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

    Neuronpedia

    INDEX
    Explanations

    rp oc play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pop
    -0.08
    _MENU
    -0.07
     Thumb
    -0.06
     makeover
    -0.06
    .tb
    -0.06
     Charges
    -0.06
    IDX
    -0.06
     means
    -0.06
     poner
    -0.06
    Dia
    -0.06
    POSITIVE LOGITS
     junit
    0.06
    ्रस
    0.06
     محصولات
    0.06
     oddly
    0.06
    座
    0.06
     ž
    0.06
    opup
    0.06
    hospital
    0.05
    .pt
    0.05
     fís
    0.05
    Act Density 0.004%

    No Known Activations