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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jur
    -0.06
    /w
    -0.06
     hoc
    -0.06
    (pkt
    -0.06
     ng
    -0.06
     Counts
    -0.06
    });↵
    -0.06
     S
    -0.06
    iv
    -0.06
     gia
    -0.06
    POSITIVE LOGITS
     цих
    0.07
     Его
    0.07
    ็กชาย
    0.06
     happiest
    0.06
     svaz
    0.06
    agento
    0.06
    ，为
    0.06
     DRV
    0.06
    _OPERATOR
    0.06
     llama
    0.06
    Act Density 0.060%

    No Known Activations