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

    Neuronpedia

    INDEX
    Explanations

    actual / true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unlike
    0.48
    upas
    0.43
     Strategies
    0.40
     Adaptive
    0.40
    ังหว
    0.39
     Muchos
    0.39
    usc
    0.38
     One
    0.38
     Many
    0.38
     Fast
    0.38
    POSITIVE LOGITS
     verdadeira
    0.56
     véritable
    0.54
     verdadera
    0.52
     bona
    0.47
     meaningful
    0.46
     verdadeiro
    0.46
    實際
    0.45
     actual
    0.45
    真正
    0.44
    真正的
    0.43
    Act Density 0.101%

    No Known Activations