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

    Neuronpedia

    INDEX
    Explanations

    words related to research methodologies and scientific terminology

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

    both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NodeId
    -0.52
     Nova
    -0.50
    Nova
    -0.48
     Crucible
    -0.45
     Classic
    -0.45
     Hammer
    -0.44
     propOrder
    -0.44
    thal
    -0.44
     Tampa
    -0.44
     Orbit
    -0.43
    POSITIVE LOGITS
    endpush
    0.59
     wikipagina
    0.57
     snippetHide
    0.52
     keduanya
    0.52
    ValueStyle
    0.49
    awtextra
    0.49
     entrambi
    0.49
     beide
    0.48
     båda
    0.47
     Beide
    0.46
    Act Density 0.056%

    No Known Activations