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

    Neuronpedia

    INDEX
    Explanations

    irrational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuss
    -0.08
     holder
    -0.07
    toThrow
    -0.07
     pon
    -0.07
    lied
    -0.07
    θε
    -0.07
    ш
    -0.07
    isti
    -0.07
     Provision
    -0.06
    $out
    -0.06
    POSITIVE LOGITS
     Saskatchewan
    0.15
     Barack
    0.15
     irrational
    0.15
     Labrador
    0.14
     racism
    0.14
     multiprocessing
    0.14
     interracial
    0.12
     Interracial
    0.11
    atchewan
    0.09
    rocessing
    0.08
    Act Density 0.005%

    No Known Activations