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

    Neuronpedia

    INDEX
    Explanations

    programming conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.99
    3
    0.85
    apple
    0.81
    1
    0.80
    ii
    0.80
    4
    0.79
    ive
    0.78
    ’
    0.77
    Kids
    0.76
    j
    0.76
    POSITIVE LOGITS
     jurisdict
    0.85
     fief
    0.79
    ্প
    0.76
     discern
    0.75
     CAGR
    0.74
    வர்களாக
    0.74
     patric
    0.73
     bijective
    0.72
     USDC
    0.71
    RECTION
    0.71
    Act Density 0.009%

    No Known Activations