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

    Neuronpedia

    INDEX
    Explanations

    0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ро
    0.76
    STONE
    0.75
    но
    0.75
     peripherals
    0.72
     encephalitis
    0.72
    COL
    0.67
     จับ
    0.67
    ज़र
    0.66
     municip
    0.66
     exacte
    0.63
    POSITIVE LOGITS
     النهار
    0.92
    imate
    0.90
    mathop
    0.90
    𝚍
    0.90
    atthena
    0.89
     nebo
    0.89
     малы
    0.88
     keuangan
    0.88
     suas
    0.88
    formance
    0.87
    Act Density 0.001%

    No Known Activations