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

    Neuronpedia

    INDEX
    Explanations

    numerical representations of percentages and statistics

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

    Numbers ending in -ty

    np_acts-logits-general · gemini-2.0-flash

    numbers ending in ty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.79
    yntaxException
    -0.74
    IntoConstraints
    -0.69
    клопе
    -0.67
     GenerationType
    -0.66
     ProtoMessage
    -0.64
     WaitForSeconds
    -0.61
    formik
    -0.59
     ddelweddau
    -0.59
    WebServlet
    -0.59
    POSITIVE LOGITS
     thirty
    0.72
     eighty
    0.72
     percent
    0.72
    something
    0.71
     something
    0.71
     sixty
    0.71
     twenty
    0.70
     fifty
    0.69
     ninety
    0.67
    two
    0.66
    Act Density 0.082%

    No Known Activations