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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .RequestParam
    -0.07
    _slots
    -0.07
     Maine
    -0.06
     acad
    -0.06
     jpeg
    -0.06
     EXEMPLARY
    -0.06
     Indiana
    -0.06
     Lawyers
    -0.06
     neger
    -0.06
    αιν
    -0.06
    POSITIVE LOGITS
     constr
    0.08
     pre
    0.07
    .subtract
    0.06
    unun
    0.06
    ΟΥΛ
    0.06
    edback
    0.06
    co
    0.06
    �
    0.06
    _mD
    0.06
    投资
    0.06
    Act Density 0.016%

    No Known Activations