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

    Neuronpedia

    INDEX
    Explanations

    latex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nas
    -0.08
    Phone
    -0.07
     boiling
    -0.07
     Hawk
    -0.07
     nas
    -0.06
     Rou
    -0.06
    _Check
    -0.06
     العرب
    -0.06
     eventData
    -0.06
     Trophy
    -0.06
    POSITIVE LOGITS
    ในส
    0.07
     poisoned
    0.07
     installment
    0.07
     freshman
    0.06
     процесс
    0.06
     persistent
    0.06
     función
    0.06
    xcf
    0.06
    ceso
    0.06
    different
    0.06
    Act Density 0.005%

    No Known Activations