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

    Neuronpedia

    INDEX
    Explanations

    treat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -effective
    -0.08
     configFile
    -0.07
     Verde
    -0.07
     doorstep
    -0.07
     fractional
    -0.06
    憑
    -0.06
     closeButton
    -0.06
     december
    -0.06
    _recv
    -0.06
     день
    -0.06
    POSITIVE LOGITS
    ule
    0.07
    .Payment
    0.07
    .tr
    0.07
     horrors
    0.07
    שואה
    0.07
     pickup
    0.06
     unspecified
    0.06
    ⊔
    0.06
    ulled
    0.06
    垕
    0.06
    Act Density 0.078%

    No Known Activations