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

    Neuronpedia

    INDEX
    Explanations

    nc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igne
    -0.07
     integrated
    -0.06
     tty
    -0.06
    驶
    -0.06
    ीप
    -0.06
    หว
    -0.06
    _inputs
    -0.05
    Jet
    -0.05
     transporter
    -0.05
    Serial
    -0.05
    POSITIVE LOGITS
    жі
    0.07
     Associate
    0.07
    wagon
    0.06
     sheriff
    0.06
     Sheriff
    0.06
    aise
    0.06
     Hampshire
    0.06
     설치
    0.06
     -------↵
    0.06
    chain
    0.06
    Act Density 0.000%

    No Known Activations