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

    Neuronpedia

    INDEX
    Explanations

    Research project timelines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    正在
    -0.06
     Ibrahim
    -0.06
    Benefits
    -0.06
    empre
    -0.06
     predecessors
    -0.06
    гля
    -0.06
    .endpoint
    -0.05
     hun
    -0.05
    trail
    -0.05
     диза
    -0.05
    POSITIVE LOGITS
    ۲
    0.07
    trand
    0.07
     củ
    0.07
    _cos
    0.07
    ^{
    0.07
     Poz
    0.06
    pv
    0.06
    638
    0.06
    .COL
    0.06
    ')==
    0.06
    Act Density 0.042%

    No Known Activations