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

    Neuronpedia

    INDEX
    Explanations

    Hand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hand
    -0.49
     Bes
    -0.44
    离
    -0.43
     sp
    -0.40
    wand
    -0.40
     coup
    -0.39
    popd
    -0.38
    Specyfikacja
    -0.38
     Fe
    -0.38
    רוב
    -0.38
    POSITIVE LOGITS
    ing
    1.09
    er
    1.00
    ed
    0.99
    ième
    0.90
     تضيفلها
    0.89
    ی
    0.89
    adecimal
    0.87
    expandindo
    0.84
    arithmic
    0.81
    parsedMessage
    0.80
    Act Density 0.679%

    No Known Activations