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

    Neuronpedia

    INDEX
    Explanations

    references to governmental or authoritative figures and their actions

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

    foreign names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.66
    ỡng
    -0.59
    ########.
    -0.58
     istrinya
    -0.57
     damska
    -0.53
    جوايز
    -0.51
     raiſ
    -0.51
     abger
    -0.51
    */),
    -0.50
     julk
    -0.50
    POSITIVE LOGITS
    featureID
    0.45
     thus
    0.40
    .
    0.37
     transfieras
    0.36
    كويكب
    0.35
     Numerade
    0.34
    RegistryLite
    0.32
    thus
    0.32
     defaultstate
    0.32
    printStackTrace
    0.31
    Act Density 0.266%

    No Known Activations