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

    Neuronpedia

    INDEX
    Explanations

    minimum and maximum values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Envelope
    -0.08
     grids
    -0.07
    不超过
    -0.07
    快三
    -0.06
    _debug
    -0.06
    plot
    -0.06
    heartbeat
    -0.06
     суд
    -0.06
     Eduardo
    -0.06
     Chairs
    -0.06
    POSITIVE LOGITS
    .fillStyle
    0.07
    ürü
    0.07
    勇
    0.07
    FORMANCE
    0.07
     malls
    0.07
    back
    0.07
    _kel
    0.06
     undermin
    0.06
    IFO
    0.06
     fenced
    0.06
    Act Density 0.011%

    No Known Activations