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

    Neuronpedia

    INDEX
    Explanations

    astronomy and physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suav
    -0.08
     enrol
    -0.08
    学历
    -0.08
     IAM
    -0.08
     betaald
    -0.07
     smooth
    -0.07
     sufficiently
    -0.07
     imitation
    -0.07
    payer
    -0.07
    -paying
    -0.07
    POSITIVE LOGITS
    0.08
     enhance
    0.08
    identify
    0.08
    zzz
    0.07
     coordinating
    0.07
     disaster
    0.07
     identify
    0.07
    incident
    0.07
    ׳
    0.07
    Incident
    0.07
    Act Density 0.001%
    No Known Activations