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

    Neuronpedia

    INDEX
    Explanations

    terms associated with community engagement and participation in events

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

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     however
    -0.57
    @[+][
    -0.48
    
    -0.46
    However
    -0.45
    Erstellt
    -0.43
     jedoch
    -0.43
     ModelExpression
    -0.43
    +:+
    -0.42
     však
    -0.42
     kuitenkin
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.56
     Roskov
    0.54
     Италијани
    0.49
     queſta
    0.44
     endblock
    0.43
     betweenstory
    0.42
     hochzeit
    0.42
    ddots
    0.41
     Italijanski
    0.41
    rungsseite
    0.40
    Act Density 0.172%

    No Known Activations