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

    Neuronpedia

    INDEX
    Explanations

    references or citations in academic or formal texts

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

    list formatting and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     überg
    -0.46
     tarjo
    -0.42
     weiterer
    -0.40
    seguida
    -0.40
     weiteres
    -0.40
     sogen
    -0.40
     gerekiyor
    -0.38
    Carriera
    -0.37
     podjet
    -0.36
     therefore
    -0.36
    POSITIVE LOGITS
     Italijanski
    0.65
     informée
    0.60
    tagHelperRunner
    0.56
     Италијани
    0.56
     betweenstory
    0.53
    ❋
    0.52
     kasarigan
    0.52
    OGND
    0.50
     nonUne
    0.50
    ChrTalk
    0.50
    Act Density 0.022%

    No Known Activations