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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions of possibility or necessity

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

    mix of german and french conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NA
    -0.35
    Ộ
    -0.34
     couteau
    -0.34
     enví
    -0.33
     âme
    -0.32
     compositeur
    -0.32
    ensuche
    -0.31
    États
    -0.31
    Kết
    -0.31
     ennemi
    -0.30
    POSITIVE LOGITS
    citroën
    0.68
    niſſe
    0.67
     AssemblyVersion
    0.66
    ſehen
    0.66
    følgelig
    0.65
    setVerticalGroup
    0.62
    EDEFAULT
    0.62
     utafitiHapana
    0.62
    verwijs
    0.62
     very
    0.61
    Act Density 0.007%

    No Known Activations