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

    Neuronpedia

    INDEX
    Explanations

    ulated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    одо
    -0.07
     effectively
    -0.07
     ruler
    -0.07
    Lu
    -0.06
    approve
    -0.06
     Lu
    -0.06
     arist
    -0.06
     ─
    -0.06
    ................................................................
    -0.06
    ornado
    -0.06
    POSITIVE LOGITS
     aging
    0.07
    _obj
    0.06
     deceived
    0.06
    (Packet
    0.06
    _exempt
    0.06
    getIndex
    0.06
    _attachment
    0.06
    球
    0.06
    丹
    0.06
    切
    0.06
    Act Density 0.004%

    No Known Activations