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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elta
    -0.07
     decay
    -0.07
     уб
    -0.06
     pu
    -0.06
     počíta
    -0.06
    θος
    -0.06
    lope
    -0.06
    ++.
    -0.06
    _translation
    -0.06
    요
    -0.06
    POSITIVE LOGITS
     enormous
    0.06
    toBeTruthy
    0.06
    ONS
    0.06
    /manage
    0.06
    assium
    0.06
    SpecWarn
    0.06
    男性
    0.06
     Broncos
    0.06
    otyping
    0.06
    Lbl
    0.06
    Act Density 0.107%

    No Known Activations