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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utility
    -0.08
    ıt
    -0.07
     Holocaust
    -0.06
     Summary
    -0.06
     Fees
    -0.06
    Period
    -0.06
    Slider
    -0.06
     Kai
    -0.06
     Hutchinson
    -0.06
    Sand
    -0.06
    POSITIVE LOGITS
     brasile
    0.07
    %H
    0.07
    \Action
    0.07
    arged
    0.06
    _EVENTS
    0.06
    しました
    0.06
     Initialize
    0.06
    .kr
    0.06
    strategy
    0.06
     通
    0.06
    Act Density 0.005%

    No Known Activations