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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references related to ratings, identification, and classifications

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

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.38
     “
    -0.27
     \
    -0.27
    -
    -0.26
    <strong>
    -0.26
    ↵
    -0.26
     v
    -0.25
     '
    -0.24
    ponente
    -0.24
     p
    -0.24
    POSITIVE LOGITS
    #+#
    0.82
    expandindo
    0.79
     HasFactory
    0.79
    ⟬
    0.79
    <pad>
    0.76
     ब्रेकडाउन
    0.76
    <unused43>
    0.75
    <unused3>
    0.75
    <unused8>
    0.75
    <unused14>
    0.75
    Act Density 0.059%

    No Known Activations