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

    Neuronpedia

    INDEX
    Explanations

    trading parameters and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Richard
    0.41
     RICHARD
    0.41
     غیر
    0.39
    axies
    0.38
    discipline
    0.38
     Blood
    0.38
     GridLayout
    0.37
    etu
    0.37
     Pierce
    0.37
     Concepción
    0.37
    POSITIVE LOGITS
     lot
    0.39
    Nin
    0.37
     lote
    0.37
     eas
    0.36
     MQ
    0.36
     propriedades
    0.36
    Nah
    0.35
    Charter
    0.35
    GPT
    0.35
     povo
    0.35
    Act Density 0.013%

    No Known Activations