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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references in a citation format

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

    publication citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -0.61
     Theſe
    -0.60
     becauſe
    -0.57
    prehensive
    -0.57
    +)/
    -0.56
     CreateTagHelper
    -0.56
     beſt
    -0.53
    ]),
    -0.53
     fubject
    -0.53
     tranſ
    -0.52
    POSITIVE LOGITS
    InputTagHelper
    0.57
     AssemblyProduct
    0.56
    roën
    0.51
    quatch
    0.50
    __':
    0.50
    AsUp
    0.49
    AutoModerator
    0.48
     الحره
    0.45
    Chham
    0.44
    __':
    0.44
    Act Density 0.412%

    No Known Activations