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

    Neuronpedia

    INDEX
    Explanations

    pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    769
    -0.07
    _Com
    -0.07
     zu
    -0.06
     extremism
    -0.06
    022
    -0.06
     Loss
    -0.06
    izm
    -0.06
    ooth
    -0.06
    .Ui
    -0.06
    onder
    -0.06
    POSITIVE LOGITS
    #g
    0.06
     ntohs
    0.06
     INA
    0.06
    mast
    0.06
     корол
    0.06
    (Print
    0.06
    serialize
    0.06
    French
    0.06
    ố
    0.06
    ).'
    0.06
    Act Density 0.003%

    No Known Activations