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

    Neuronpedia

    INDEX
    Explanations

    acceptance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     товар
    0.81
     объект
    0.79
     mecanismos
    0.78
     себя
    0.77
     прежде
    0.75
    続きを読む
    0.75
    UART
    0.75
     defam
    0.74
     Susp
    0.73
     MQTT
    0.73
    POSITIVE LOGITS
    it
    1.13
    al
    0.96
    ono
    0.90
    c
    0.89
    ك
    0.87
    et
    0.87
    ри
    0.84
    bons
    0.84
    inizi
    0.84
    ir
    0.82
    Act Density 0.004%

    No Known Activations