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

    Neuronpedia

    INDEX
    Explanations

    research and technical details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Roles
    -0.07
    ек
    -0.07
     колич
    -0.07
    _succ
    -0.07
     SER
    -0.07
    .contentSize
    -0.07
     Jessica
    -0.06
     bpm
    -0.06
    Jessica
    -0.06
    马
    -0.06
    POSITIVE LOGITS
     آپ
    0.06
    asley
    0.06
    iropr
    0.06
    payer
    0.06
     tha
    0.06
    闘
    0.06
    dh
    0.06
     restrain
    0.06
     kh
    0.06
    .exe
    0.06
    Act Density 0.000%

    No Known Activations