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

    Neuronpedia

    INDEX
    Explanations

    bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elvis
    -0.07
     Vend
    -0.06
    <AudioSource
    -0.06
    フォ
    -0.06
     buffalo
    -0.06
     Tür
    -0.06
     zdroj
    -0.06
    egas
    -0.06
     assail
    -0.06
     Söz
    -0.06
    POSITIVE LOGITS
    -bit
    0.07
    '";↵
    0.07
     ";↵↵
    0.07
    daughter
    0.07
    Cb
    0.07
    controlled
    0.07
    Л
    0.07
    ";↵↵
    0.07
    ;
↵
↵
    0.06
    ीत
    0.06
    Act Density 0.002%

    No Known Activations