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

    Neuronpedia

    INDEX
    Explanations

    graphical representations and figures in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File names in image tags

    np_acts-logits-general · gemini-2.0-flash

    image references and figure numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -1.02
     itſelf
    -1.02
    OGND
    -0.86
    complexContent
    -0.85
     Houſe
    -0.83
    kháu
    -0.83
    enumi
    -0.82
     Мексичка
    -0.81
    WarningLevel
    -0.81
     незавершена
    -0.81
    POSITIVE LOGITS
    <eos>
    0.84
    ↵↵
    0.75
    \\
    0.69
    ↵
    0.65
    ↵↵↵
    0.65
    ↵↵↵↵
    0.62
    ↵↵↵↵↵
    0.51
    ↵↵↵↵↵↵
    0.48
    ꒳
    0.48
    .\\
    0.48
    Act Density 0.342%

    No Known Activations