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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of semantics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    semantics or deleterious effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuerdas
    -0.46
     financieras
    -0.46
     vectorielles
    -0.42
     salário
    -0.41
     financieros
    -0.41
     prácticas
    -0.41
     científicas
    -0.41
     universelle
    -0.41
     jorden
    -0.41
    CONFIGURATION
    -0.41
    POSITIVE LOGITS
     تا
    1.74
    تا
    1.05
    addPreferredGap
    0.60
     ujednoznacz
    0.60
     IBOutlet
    0.59
    tagHelperRunner
    0.59
    点此举报
    0.59
    تقاوى
    0.59
    ########.
    0.59
     MainAxisSize
    0.58
    Act Density 0.002%

    No Known Activations