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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кто
    -0.07
     alleged
    -0.06
    Saturday
    -0.06
     srdce
    -0.06
    consistent
    -0.06
    iedy
    -0.06
     آل
    -0.06
    status
    -0.06
    -office
    -0.06
    issues
    -0.06
    POSITIVE LOGITS
     Bud
    0.06
    вай
    0.06
    缩
    0.06
    _Execute
    0.06
    ,ll
    0.06
    ゛
    0.06
    (obs
    0.06
    _BUF
    0.06
     socio
    0.06
     SDL
    0.06
    Act Density 0.014%

    No Known Activations