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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	st
    -0.07
    lowest
    -0.07
    _tim
    -0.07
    -car
    -0.07
    -0.06
    -0.06
    _context
    -0.06
     latency
    -0.06
     застосов
    -0.06
     billing
    -0.06
    POSITIVE LOGITS
    li
    0.07
    -operative
    0.07
     Mirror
    0.06
     hai
    0.06
     muestra
    0.06
    :::::::::::
    0.06
    .scala
    0.06
    .А
    0.06
     LATIN
    0.06
    lamaya
    0.06
    Act Density 0.021%

    No Known Activations