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

    Neuronpedia

    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cost
    -0.07
     hedge
    -0.06
    텐
    -0.06
    Orders
    -0.06
    lds
    -0.06
    imizeBox
    -0.06
     thiểu
    -0.06
     Blood
    -0.06
     nightmare
    -0.05
     ως
    -0.05
    POSITIVE LOGITS
     fit
    0.08
     unfit
    0.07
     Fit
    0.07
     DataRow
    0.07
     kişinin
    0.07
    spawn
    0.07
     curly
    0.07
     Independ
    0.06
     emulation
    0.06
    Spin
    0.06
    Act Density 0.009%

    No Known Activations