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

    Neuronpedia

    INDEX
    Explanations

    line breaks and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৭
    0.86
    7
    0.83
    5
    0.78
    8
    0.76
    erus
    0.75
    ٨
    0.75
    ethe
    0.72
    4
    0.72
    es
    0.70
    ue
    0.69
    POSITIVE LOGITS
    та
    0.93
    ج
    0.80
     and
    0.73
     combina
    0.71
     esegu
    0.71
    هاي
    0.71
    ला
    0.70
    मा
    0.70
     will
    0.70
    าย
    0.69
    Act Density 0.000%

    No Known Activations