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

    Neuronpedia

    INDEX
    Explanations

    personal stories/recollections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    comment
    -0.07
     orphan
    -0.06
     faith
    -0.06
    HANDLE
    -0.06
    Christ
    -0.06
     반
    -0.06
     capit
    -0.06
     rebel
    -0.06
    Fri
    -0.06
    Friday
    -0.06
    POSITIVE LOGITS
    eming
    0.07
     ticari
    0.07
     Psych
    0.07
    .Security
    0.06
    _es
    0.06
    roids
    0.06
    .pos
    0.06
    iated
    0.06
     Analyst
    0.06
     Educ
    0.06
    Act Density 0.002%

    No Known Activations