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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     established
    -0.82
    ades
    -0.82
    established
    -0.68
     Established
    -0.68
    Established
    -0.68
    absorption
    -0.66
     vallée
    -0.63
     absorption
    -0.62
     establecido
    -0.62
    føl
    -0.60
    POSITIVE LOGITS
    s
    0.72
    ی
    0.60
     noqa
    0.57
    sous
    0.55
     helico
    0.54
    +:+
    0.54
    ski
    0.54
    san
    0.54
     impre
    0.54
     withal
    0.54
    Act Density 1.638%

    No Known Activations