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

    Neuronpedia

    INDEX
    Explanations

    references to figures, tables, and other visual data representations in a document

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    citation figures and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    とり
    -0.49
     R
    -0.46
     meub
    -0.43
    куда
    -0.43
     motore
    -0.43
     Reinh
    -0.42
    rtf
    -0.42
     move
    -0.42
    newtheorem
    -0.41
     moves
    -0.41
    POSITIVE LOGITS
    〢
    0.72
    ніципалі
    0.71
     endblock
    0.70
     تانيه
    0.70
    ㅢ
    0.70
     becauſe
    0.70
    ynchronously
    0.68
    ">//
    0.66
    ㅐ
    0.65
    continence
    0.65
    Act Density 0.335%

    No Known Activations