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

    Neuronpedia

    INDEX
    Explanations

    numbers differ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.44
    Repeating
    0.41
    '
    0.40
     manifestly
    0.40
    看板
    0.40
    MaxPooling
    0.39
     здесь
    0.39
    楽
    0.38
    రా
    0.37
     firmly
    0.37
    POSITIVE LOGITS
    CNR
    0.45
     Muth
    0.44
     अनुर
    0.43
    लेंट
    0.41
     Knob
    0.40
    ीकृत
    0.40
    ತರ
    0.40
     అల
    0.40
    嘗試
    0.39
     अज्ञात
    0.39
    Act Density 0.000%

    No Known Activations