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

    Neuronpedia

    INDEX
    Explanations

    prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -place
    -0.07
    롭
    -0.07
    ofil
    -0.07
     نور
    -0.06
     torrents
    -0.06
    _FC
    -0.06
    resas
    -0.06
    เจร
    -0.06
    ascular
    -0.06
    ≡
    -0.06
    POSITIVE LOGITS
     Last
    0.07
     BH
    0.07
     Throw
    0.07
    .pdf
    0.06
     ann
    0.06
    �
    0.06
     entr
    0.06
     т
    0.06
     Dent
    0.06
    ettings
    0.06
    Act Density 0.132%

    No Known Activations