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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or necessity

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

    began manufacturing, started joining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     principal
    -0.42
     prak
    -0.40
     kali
    -0.40
     PRINCIPAL
    -0.40
     principle
    -0.37
     lilla
    -0.37
     logistics
    -0.37
     nakalista
    -0.37
     Principal
    -0.36
     Warm
    -0.36
    POSITIVE LOGITS
    sizeCache
    0.53
    ActionCreators
    0.49
     zoude
    0.47
    ftagPool
    0.47
     للمعارف
    0.46
     którzy
    0.46
     estekak
    0.46
    GOTREF
    0.46
     twij
    0.45
     bezoekers
    0.45
    Act Density 0.070%

    No Known Activations