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

    Neuronpedia

    INDEX
    Explanations

    say "P" or "PH"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _adjust
    -0.07
    /,
    -0.07
    iasi
    -0.06
    /database
    -0.06
    jeme
    -0.06
    video
    -0.06
    특별
    -0.06
    [];↵↵
    -0.06
    문
    -0.06
     hip
    -0.06
    POSITIVE LOGITS
     Andr
    0.07
     absol
    0.06
    -lnd
    0.06
     mutually
    0.06
    άνι
    0.06
    _ans
    0.06
     bunu
    0.06
     seg
    0.06
     Пет
    0.06
     yasak
    0.06
    Act Density 0.001%

    No Known Activations