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

    Neuronpedia

    INDEX
    Explanations

    instances of proposals and suggestions

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

    "proposed"

    np_acts-logits-general · gemini-2.0-flash

    proposed methods or ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atikan
    -0.55
    Très
    -0.53
     Karin
    -0.52
     waktu
    -0.50
    actéristi
    -0.49
    Colores
    -0.49
     informace
    -0.49
    MEMORY
    -0.48
     Kingston
    -0.48
     pamięci
    -0.47
    POSITIVE LOGITS
     proposal
    1.06
     Proposal
    0.97
     proposals
    0.93
     proposed
    0.90
     propose
    0.87
    Proposal
    0.87
     Proposals
    0.84
    proposal
    0.82
     Proposed
    0.79
     proposing
    0.79
    Act Density 0.222%

    No Known Activations