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

    Neuronpedia

    INDEX
    Explanations

    actions or decisions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নয়
    0.62
     nervioso
    0.58
     работает
    0.57
     анима
    0.56
     japonés
    0.56
     emocional
    0.55
     oeste
    0.55
     animación
    0.54
    动画
    0.54
     participaron
    0.54
    POSITIVE LOGITS
     proclamation
    0.62
     breach
    0.60
     proclam
    0.59
     breaches
    0.59
     send
    0.59
     proclaimed
    0.58
     expedient
    0.58
     decreed
    0.58
     abrog
    0.58
     enforce
    0.57
    Act Density 0.000%

    No Known Activations