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

    Neuronpedia

    INDEX
    Explanations

    `__init__` method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countenance
    0.36
     hummingbird
    0.36
     Ruf
    0.36
     سننے
    0.36
     runaway
    0.35
     whining
    0.35
    ӗ
    0.34
     monotony
    0.34
     기다
    0.34
     woodpe
    0.34
    POSITIVE LOGITS
     distant
    0.38
     tế
    0.36
     distante
    0.36
    ூட்
    0.35
     EBR
    0.35
     আট
    0.35
     účast
    0.35
     اچ
    0.35
    PLEMENT
    0.34
    Helmet
    0.33
    Act Density 0.000%

    No Known Activations