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

    Neuronpedia

    INDEX
    Explanations

    building blocks, components, foundational elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    級
    0.50
    gamer
    0.48
    spark
    0.47
    tasks
    0.47
    reactions
    0.46
    diversity
    0.46
    keyboard
    0.46
    negative
    0.46
    \#
    0.46
    (#
    0.46
    POSITIVE LOGITS
     grote
    0.55
     hém
    0.54
     mala
    0.52
     profundamente
    0.50
     margen
    0.50
     voluntad
    0.49
     understandable
    0.49
     claro
    0.48
     basé
    0.47
     simil
    0.47
    Act Density 0.004%

    No Known Activations