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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing possibility or permission

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

    may or might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.39
     quitter
    -0.36
     slut
    -0.33
    UserScript
    -0.33
     cesse
    -0.33
    switches
    -0.33
    COOK
    -0.32
     coser
    -0.32
     Leder
    -0.32
     causer
    -0.31
    POSITIVE LOGITS
    RectangleBorder
    0.64
     potete
    0.62
    ParallelGroup
    0.62
    badlogic
    0.60
     piú
    0.59
     fören
    0.58
    AndEndTag
    0.57
     raffredd
    0.57
     appunto
    0.56
    SafeMath
    0.55
    Act Density 0.032%

    No Known Activations