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

    Neuronpedia

    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (progress
    -0.08
    .progress
    -0.07
     progress
    -0.07
    	progress
    -0.07
     Berk
    -0.07
     affirmative
    -0.07
     subtree
    -0.07
    reetings
    -0.07
     Flint
    -0.07
    _PROGRESS
    -0.07
    POSITIVE LOGITS
     동안
    0.09
     الزمن
    0.09
     beträgt
    0.09
     الطويل
    0.09
     constru
    0.09
    Seconds
    0.08
    _seconds
    0.08
     construire
    0.08
     زمن
    0.08
    -lived
    0.08
    Act Density 0.005%

    No Known Activations