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

    Neuronpedia

    INDEX
    Explanations

    everyone/you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Graph
    -0.07
    _layers
    -0.07
    POINTS
    -0.07
     האדם
    -0.07
     ''
    -0.06
     tiny
    -0.06
     any
    -0.06
     transaction
    -0.06
     trails
    -0.06
     Those
    -0.06
    POSITIVE LOGITS
     Aunt
    0.07
     arson
    0.07
    ביל
    0.07
     discharged
    0.07
    𒊑
    0.07
    <translation
    0.07
    ត
    0.07
    _RESET
    0.06
    ROL
    0.06
    apache
    0.06
    Act Density 0.001%

    No Known Activations