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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hap
    0.43
    0.41
     appropri
    0.39
    लब
    0.39
    ில
    0.39
     latter
    0.38
    ны
    0.38
    शा
    0.37
    ╰
    0.36
    EZ
    0.36
    POSITIVE LOGITS
    ת
    0.56
    ate
    0.48
    ש
    0.48
    л
    0.48
    ী
    0.47
     reschedule
    0.47
    itimate
    0.47
    besiege
    0.46
     mA
    0.45
    ח
    0.45
    Act Density 0.117%

    No Known Activations