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

    Neuronpedia

    INDEX
    Explanations

    density and weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ▽
    -0.08
     ni
    -0.07
     �
    -0.07
    /configuration
    -0.07
     hexatrigesimal
    -0.07
    �
    -0.07
    .jar
    -0.07
     gracias
    -0.07
    �
    -0.07
     sog
    -0.06
    POSITIVE LOGITS
    خصص
    0.07
    쥰
    0.07
    ᴶ
    0.07
    "For
    0.07
     newArr
    0.06
    𦈡
    0.06
     Heller
    0.06
    㵐
    0.06
    _upd
    0.06
    تز
    0.06
    Act Density 0.016%

    No Known Activations