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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lod
    -0.07
     ripped
    -0.07
    965
    -0.07
     piano
    -0.06
     aussi
    -0.06
     bloodstream
    -0.06
    _exempt
    -0.06
    	actor
    -0.06
     господар
    -0.06
    ka
    -0.06
    POSITIVE LOGITS
     repent
    0.07
    _fb
    0.07
    users
    0.06
    ltre
    0.06
     jclass
    0.06
    ovation
    0.06
    ＿_
    0.06
    initial
    0.06
    _comment
    0.06
    account
    0.06
    Act Density 0.000%

    No Known Activations