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

    Neuronpedia

    INDEX
    Explanations

    amplitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ActivityIndicatorView
    -0.07
    -С
    -0.07
    etě
    -0.06
    ¨ط
    -0.06
    °E
    -0.06
    hů
    -0.06
    だから
    -0.06
    Throw
    -0.06
     massasje
    -0.06
    	RTLU
    -0.06
    POSITIVE LOGITS
     осві
    0.07
     emotions
    0.07
    !"
    0.07
    Episode
    0.06
     правиль
    0.06
     repro
    0.06
    _action
    0.06
     ----------------
    0.06
     checked
    0.06
    figure
    0.06
    Act Density 0.000%

    No Known Activations