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

    Neuronpedia

    INDEX
    Explanations

    file paths and emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    README
    -0.07
    undred
    -0.07
    olders
    -0.07
    onestly
    -0.06
     καθ
    -0.06
     playful
    -0.06
     sexual
    -0.06
    ollywood
    -0.06
    /non
    -0.06
    party
    -0.06
    POSITIVE LOGITS
    H
    0.11
     H
    0.11
     Harrison
    0.10
     haul
    0.10
    .H
    0.10
     HM
    0.09
     HB
    0.09
    -h
    0.09
     Ho
    0.09
     Hale
    0.09
    Act Density 0.491%

    No Known Activations