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

    Neuronpedia

    INDEX
    Explanations

    elements of mathematical notation, particularly those related to absolute values and inequalities

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

    Mathematical or symbolic notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.77
    oneofs
    -0.69
    MessageOf
    -0.66
    ftagPool
    -0.65
    MergeFrom
    -0.63
    DockStyle
    -0.60
    GraphicsUnit
    -0.56
    parsedMessage
    -0.55
    //
    -0.53
     Италијани
    -0.52
    POSITIVE LOGITS
    +|
    0.84
     |
    0.73
    -|
    0.72
    _|
    0.69
    .|
    0.69
    iële
    0.68
     Others
    0.64
     $|
    0.63
    ]|
    0.61
     others
    0.61
    Act Density 0.182%

    No Known Activations