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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entropy
    -0.08
     stellen
    -0.07
    _POLL
    -0.07
    (random
    -0.06
    facet
    -0.06
    ifr
    -0.06
    onical
    -0.06
     Geek
    -0.06
    _pg
    -0.06
    _female
    -0.06
    POSITIVE LOGITS
     academics
    0.06
    .ErrorCode
    0.06
     Fed
    0.06
     occult
    0.06
    ชอบ
    0.06
    anim
    0.06
     Vlad
    0.06
    Estimated
    0.06
     cụ
    0.06
    tableName
    0.06
    Act Density 0.026%

    No Known Activations