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

    Neuronpedia

    INDEX
    Explanations

    spectral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Damage
    -0.08
    Amount
    -0.07
     endDate
    -0.07
     території
    -0.07
     blouse
    -0.07
     cidade
    -0.07
     manera
    -0.07
     machen
    -0.07
    ynchronize
    -0.07
    confirm
    -0.07
    POSITIVE LOGITS
     spectral
    0.11
    pectral
    0.08
    ral
    0.06
    |R
    0.06
    _SSL
    0.06
     hr
    0.06
    lil
    0.06
     впол
    0.06
     politic
    0.06
     příliš
    0.06
    Act Density 0.001%

    No Known Activations