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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convincing
    -0.07
    てい
    -0.06
    RET
    -0.06
    ไว
    -0.06
    _SAN
    -0.06
     قرآن
    -0.06
     дво
    -0.06
    _ENT
    -0.06
     با
    -0.06
    796
    -0.06
    POSITIVE LOGITS
    invoke
    0.07
     penny
    0.07
    veys
    0.06
     Globe
    0.06
    _Free
    0.06
    (guid
    0.06
    .getContentPane
    0.06
    (optimizer
    0.06
     guidelines
    0.06
     fill
    0.06
    Act Density 0.011%

    No Known Activations