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

    Neuronpedia

    INDEX
    Explanations

    words related to something getting worse

    oai_token-act-pair · gemini-2.0-flash

    expressing opinions/conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Демографія
    -0.99
    ValueStyle
    -0.85
    UrlResolution
    -0.85
    setVerticalGroup
    -0.84
     InputDecoration
    -0.84
     متعلقه
    -0.78
     AttributeSet
    -0.77
     AssemblyTitle
    -0.77
    enumi
    -0.73
    IndentedString
    -0.71
    POSITIVE LOGITS
     each
    0.48
    cula
    0.47
     Each
    0.44
     chaque
    0.41
    GeneratedCode
    0.41
    ,
    0.40
    Each
    0.39
     asal
    0.39
    each
    0.38
     masing
    0.37
    Act Density 0.664%

    No Known Activations