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

    Neuronpedia

    INDEX
    Explanations

    beyond human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tremors
    0.63
     microphones
    0.46
     anisotrop
    0.45
     confrontations
    0.43
     trasera
    0.43
    ள்ளனர்
    0.43
     choirs
    0.42
     trabajos
    0.42
     tremor
    0.42
     অনেকে
    0.41
    POSITIVE LOGITS
    c
    0.50
    ಕ್
    0.49
     草
    0.49
    业务
    0.48
    purpose
    0.48
    定
    0.47
     定
    0.46
    wala
    0.45
    ding
    0.45
    不会
    0.45
    Act Density 0.002%

    No Known Activations