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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    图片
    -0.07
    $db
    -0.06
     sqr
    -0.06
    脂
    -0.06
    říz
    -0.06
     Bird
    -0.06
    EI
    -0.06
    १९
    -0.06
    41
    -0.06
    ์ท
    -0.06
    POSITIVE LOGITS
    えた
    0.06
    scient
    0.06
     frustrations
    0.06
     investigative
    0.06
     SEEK
    0.06
    .work
    0.06
     edilm
    0.06
     approaching
    0.06
    лід
    0.06
    ´:
    0.06
    Act Density 0.004%

    No Known Activations