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

    Neuronpedia

    INDEX
    Explanations

    references to accessibility of information or resources

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

    accessible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.50
    ing
    -0.48
     Suivez
    -0.46
     vœ
    -0.43
     or
    -0.43
     appunt
    -0.41
    <bos>
    -0.40
     énon
    -0.40
     war
    -0.40
    ING
    -0.40
    POSITIVE LOGITS
    accessible
    1.81
     accessible
    1.81
     Accessible
    1.76
    Accessible
    1.64
     accesible
    1.32
     accesibles
    1.27
     accessibles
    1.24
     inaccessible
    1.23
     accessibility
    1.18
    Accessibility
    1.13
    Act Density 0.003%

    No Known Activations