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

    Neuronpedia

    INDEX
    Explanations

    warm and cold states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ணற
    0.99
     Lá
    0.97
    lesson
    0.93
     Absolutely
    0.93
    ”)
    0.92
    anto
    0.92
    レー
    0.90
     Paradigm
    0.90
     informação
    0.89
     Evaluación
    0.89
    POSITIVE LOGITS
    blooded
    1.02
    th
    0.76
    कालीन
    0.74
     취
    0.74
    취
    0.73
    ный
    0.73
     el
    0.72
    '<
    0.70
    hearted
    0.69
    elda
    0.68
    Act Density 0.195%

    No Known Activations