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

    Neuronpedia

    INDEX
    Explanations

    studies and experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    られる
    -0.08
    Operator
    -0.07
    TCHA
    -0.07
     захисту
    -0.07
    مین
    -0.06
    oland
    -0.06
    *</
    -0.06
    良
    -0.06
    尤
    -0.06
     dataIndex
    -0.06
    POSITIVE LOGITS
    utral
    0.07
     immigr
    0.07
     холод
    0.06
    (phone
    0.06
    Regards
    0.06
    /php
    0.06
    [jj
    0.06
    Called
    0.06
     McDonald
    0.06
    .nickname
    0.06
    Act Density 0.034%

    No Known Activations