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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs and syntax elements

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

    programming code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inſ
    -0.52
     Conſ
    -0.51
     Anſ
    -0.50
     Audiodateien
    -0.50
     namorados
    -0.50
     pleaſure
    -0.50
     spéciaux
    -0.49
     Monfieur
    -0.49
    <unused3>
    -0.49
    <unused68>
    -0.48
    POSITIVE LOGITS
     again
    0.43
    KURZBESCHREIBUNG
    0.40
     Ban
    0.40
    WithMany
    0.39
     П
    0.38
    п
    0.37
     useAppContext
    0.37
     Again
    0.37
    **/
    0.36
    не
    0.35
    Act Density 0.032%

    No Known Activations