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

    Neuronpedia

    INDEX
    Explanations

    separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alan
    -0.07
    .ExecuteNonQuery
    -0.07
    —for
    -0.07
    Hamilton
    -0.07
     Digital
    -0.07
     sunday
    -0.06
     Football
    -0.06
    WithContext
    -0.06
     natural
    -0.06
     Basketball
    -0.06
    POSITIVE LOGITS
     <*>
    0.07
     incest
    0.07
    志
    0.06
     돌아
    0.06
     øns
    0.06
    Dé
    0.06
    .tt
    0.06
    .ascii
    0.06
    ergency
    0.06
     όμως
    0.06
    Act Density 0.051%

    No Known Activations