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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    사무
    -0.07
    Signing
    -0.07
    bum
    -0.07
    =""/>↵
    -0.07
     getBy
    -0.07
    |(↵
    -0.07
    ⵣ
    -0.07
    ('')↵
    -0.06
    왠
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     devastating
    0.07
     Padding
    0.07
     KS
    0.07
     located
    0.07
    는데
    0.07
     feat
    0.07
    นะคะ
    0.07
    ologie
    0.07
    ToString
    0.06
     doen
    0.06
    Act Density 0.105%

    No Known Activations