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

    Neuronpedia

    INDEX
    Explanations

    gest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Luis
    -0.07
    ises
    -0.07
    悅
    -0.07
     arriving
    -0.07
    סוף
    -0.07
     LL
    -0.07
     Raj
    -0.07
     thuế
    -0.07
    悦
    -0.07
    湖北
    -0.07
    POSITIVE LOGITS
    <Scalars
    0.08
    does
    0.07
    陨
    0.07
     memory
    0.07
    adal
    0.07
    סה
    0.07
     Hanging
    0.06
    合力
    0.06
    staking
    0.06
    hattan
    0.06
    Act Density 0.004%

    No Known Activations