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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Opts
    -0.07
    ạp
    -0.07
    Pure
    -0.07
    Exiting
    -0.07
    чів
    -0.06
    ились
    -0.06
    niejs
    -0.06
    較
    -0.06
     tấm
    -0.06
    合
    -0.06
    POSITIVE LOGITS
    _every
    0.07
     pj
    0.07
     Ry
    0.06
     famine
    0.06
    '
↵
↵
    0.06
     controlling
    0.06
    _First
    0.06
     """
↵
    0.06
    OutputStream
    0.06
     hustle
    0.06
    Act Density 0.038%

    No Known Activations