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

    Neuronpedia

    INDEX
    Explanations

    seeking advice or stating purpose

    np_acts-logits-general · gemini-2.5-flash-lite

    semantically salient content words—especially technical terms, action verbs, and key connectors—that carry the main informational load of a sentence.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    0.20
     titleImageUrl
    0.20
     abstr
    0.19
     enteros
    0.18
     overfitting
    0.18
     hierarch
    0.18
     melan
    0.17
     obscur
    0.17
     ridiculus
    0.17
    🦐
    0.17
    POSITIVE LOGITS
    0.25
     I
    0.21
    з
    0.20
    ada
    0.19
     be
    0.18
    蓣
    0.18
     UAE
    0.18
     Cricket
    0.18
    ing
    0.18
    での
    0.18
    Act Density 1.101%

    No Known Activations