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

    Neuronpedia

    INDEX
    Explanations

    references to violence and executions

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

    actions causing impact or cessation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tehdä
    -0.36
     older
    -0.34
     naturelles
    -0.33
     traditional
    -0.33
    cribir
    -0.33
     traditionnels
    -0.33
     التق
    -0.32
    Dyn
    -0.31
    RTGC
    -0.31
     Grand
    -0.31
    POSITIVE LOGITS
    TagMode
    0.53
     bezeichneter
    0.50
    󠁴
    0.48
     sentencing
    0.46
    +#+#
    0.46
    elemField
    0.46
    IsContent
    0.45
     ExecuteAsync
    0.45
    AISSEE
    0.45
    principalColumn
    0.43
    Act Density 0.045%

    No Known Activations