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

    Neuronpedia

    INDEX
    Explanations

    code / technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .poll
    -0.07
     STDMETHOD
    -0.07
    BAD
    -0.06
    ΕΤ
    -0.06
     má
    -0.06
    ประเทศ
    -0.06
     fld
    -0.06
     �
    -0.06
    （昭和
    -0.06
    macen
    -0.06
    POSITIVE LOGITS
    ệnh
    0.07
    _duration
    0.07
    ()
↵
↵
↵
    0.06
    _instances
    0.06
     S
    0.06
    Arguments
    0.06
     еще
    0.06
    layer
    0.06
    river
    0.06
    -S
    0.06
    Act Density 0.000%

    No Known Activations