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

    Neuronpedia

    INDEX
    Explanations

    subtly enhancing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izacji
    0.49
     Cities
    0.46
     Generic
    0.45
     SND
    0.45
     Antonio
    0.45
     Domestic
    0.44
    는
    0.42
     Rocca
    0.42
     Policy
    0.41
     Jurisdiction
    0.41
    POSITIVE LOGITS
     ít
    0.46
    obox
    0.45
    áns
    0.44
     продъл
    0.42
    ýt
    0.42
     đẳng
    0.41
     combinación
    0.41
    buck
    0.41
    beit
    0.40
     дорогу
    0.40
    Act Density 0.005%

    No Known Activations