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

    Neuronpedia

    INDEX
    Explanations

    sequence probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ):-
    -0.08
    nst
    -0.07
    itti
    -0.07
    -ps
    -0.06
    ируется
    -0.06
    ":"","
    -0.06
    迎来了
    -0.06
    ữu
    -0.06
    AttributeName
    -0.06
     Indices
    -0.06
    POSITIVE LOGITS
    (sem
    0.07
    娲
    0.07
     �
    0.07
     reload
    0.07
    Serializable
    0.07
    خرو
    0.06
    separator
    0.06
    ()'
    0.06
    초
    0.06
    혁
    0.06
    Act Density 0.003%

    No Known Activations