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

    Neuronpedia

    INDEX
    Explanations

    expressions related to reported speech or statements

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

    declarations and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.49
     سكانية
    -0.47
     HttpNotFound
    -0.46
    MessageTagHelper
    -0.45
     sambal
    -0.45
    ASF
    -0.44
    aarrggbb
    -0.44
    recated
    -0.43
     PDR
    -0.42
    MDL
    -0.42
    POSITIVE LOGITS
     publicly
    0.49
    说过
    0.47
     pledged
    0.44
     vouloir
    0.44
     stated
    0.43
     }{@
    0.43
     famously
    0.42
     repeatedly
    0.42
     vowed
    0.42
     instrucción
    0.41
    Act Density 0.034%

    No Known Activations