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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trigger
    -0.08
    _Call
    -0.07
    gam
    -0.07
    Дата
    -0.07
     crawling
    -0.07
    ramids
    -0.06
     Garrison
    -0.06
     trab
    -0.06
     parcels
    -0.06
     solidarity
    -0.06
    POSITIVE LOGITS
    ually
    0.08
    ;
↵
    0.07
    ／／
    0.07
    构
    0.06
    ゃ
    0.06
    的
    0.06
    .pub
    0.06
    不存在
    0.06
     prepares
    0.06
    己
    0.06
    Act Density 0.000%

    No Known Activations