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

    Neuronpedia

    INDEX
    Explanations

    titles of movies

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

    Follows quotation marks

    np_acts-logits-general · gemini-2.0-flash

    film title and description markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğından
    -0.49
    IVEREF
    -0.48
     gesammelt
    -0.47
    IContainer
    -0.47
     débit
    -0.47
     Agnew
    -0.46
    機会
    -0.46
    gwick
    -0.45
    getragen
    -0.44
    êtement
    -0.44
    POSITIVE LOGITS
     bezeichneter
    0.63
    허
    0.62
     مرئيه
    0.57
     الحره
    0.56
    ])));
    0.56
    __':
    0.55
     canst
    0.54
    ंदीखरीदारी
    0.53
    AccessorTable
    0.53
    GeneratedMessage
    0.52
    Act Density 0.123%

    No Known Activations