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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.90
    *
    0.88
    silent
    0.84
    s
    0.84
     unofficial
    0.84
     unexpected
    0.83
     carefully
    0.83
     actually
    0.83
     look
    0.83
     close
    0.83
    POSITIVE LOGITS
    ##
    1.17
     ##
    1.04
    marshalN
    0.98
    ماية
    0.90
     erschienen
    0.90
    acylglycer
    0.86
     Разби
    0.85
    0.85
     ###
    0.85
    getCQL
    0.85
    Act Density 0.212%

    No Known Activations