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

    Neuronpedia

    INDEX
    Explanations

    sequences that resemble code or script paths

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

    user inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.45
    رشف
    -0.42
    expandindo
    -0.42
    VIAF
    -0.40
     utafitiHapana
    -0.38
    DockStyle
    -0.36
    GEBURTSDATUM
    -0.35
    NameInMap
    -0.35
     VIAF
    -0.35
    FieldBuilder
    -0.35
    POSITIVE LOGITS
     $_(
    0.52
    Referências
    0.51
    eclipse
    0.51
     numeric
    0.51
     makeStyles
    0.50
    ésult
    0.49
     TensorFlow
    0.49
    fieurs
    0.49
     numerical
    0.49
     sequelize
    0.49
    Act Density 0.011%

    No Known Activations