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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngôn
    -0.08
    _NEG
    -0.06
     passe
    -0.06
     httpResponse
    -0.06
    Sony
    -0.06
    Você
    -0.06
    ervatives
    -0.06
    هره
    -0.06
    _match
    -0.06
     missed
    -0.06
    POSITIVE LOGITS
    disable
    0.07
    suit
    0.07
    oly
    0.06
     Dort
    0.06
    ption
    0.06
    /format
    0.06
    sent
    0.06
    lean
    0.06
    _OCC
    0.06
    -src
    0.06
    Act Density 0.000%

    No Known Activations