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

    Neuronpedia

    INDEX
    Explanations

    hardware requirements and speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    leer
    0.53
    LIN
    0.48
    Who
    0.47
    Кто
    0.46
    kmale
    0.45
    lema
    0.45
     Vikram
    0.45
    anjing
    0.44
    We
    0.44
    vish
    0.44
    POSITIVE LOGITS
    ブ
    0.50
     ajust
    0.50
     reproducibility
    0.47
     computador
    0.47
    副作用
    0.47
    뷸
    0.46
     ox
    0.46
     adjust
    0.46
    殭
    0.45
     summarizes
    0.45
    Act Density 0.003%

    No Known Activations