Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Crotian language snippets about Facebook accounts, especially anything enclosed in quotation marks

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    mixed content texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    featureID
    -0.74
    BeginInit
    -0.66
    tanleria
    -0.65
    elemField
    -0.60
    TagMode
    -0.59
     referenties
    -0.58
    DockStyle
    -0.58
     Normdatei
    -0.52
    addComponent
    -0.51
     henvisninger
    -0.51
    POSITIVE LOGITS
     createSlice
    0.51
    ViewFeatures
    0.49
     himo
    0.49
    vena
    0.48
    modb
    0.47
     <=",
    0.46
     ecclesiastical
    0.44
    EXT
    0.43
    ArrowToggle
    0.43
    Capítulo
    0.42
    Act Density 0.534%

    No Known Activations