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

    Neuronpedia

    INDEX
    Explanations

    say [ words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sensors
    -0.07
     differential
    -0.07
    -html
    -0.07
     Optimization
    -0.07
     grinder
    -0.06
    getNum
    -0.06
     incest
    -0.06
    '|
    -0.06
     pom
    -0.06
     volts
    -0.06
    POSITIVE LOGITS
    eldon
    0.07
    활동
    0.07
    .receive
    0.06
     occupy
    0.06
    ercise
    0.06
     Eş
    0.06
     odpověd
    0.06
     říj
    0.06
    _single
    0.06
     captain
    0.06
    Act Density 0.006%

    No Known Activations