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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()['
    -0.08
    SHORT
    -0.07
     sulla
    -0.07
     Pt
    -0.06
     coc
    -0.06
    -image
    -0.06
    queen
    -0.06
     Lad
    -0.06
    озвращает
    -0.06
    cete
    -0.06
    POSITIVE LOGITS
    AVIS
    0.07
    _ABORT
    0.06
    ネット
    0.06
    -efficient
    0.06
     elo
    0.06
    fullname
    0.06
    aviour
    0.06
     губер
    0.06
    rol
    0.06
    。</
    0.06
    Act Density 0.010%

    No Known Activations