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

    Neuronpedia

    INDEX
    Explanations

    references to actions, particularly those involving illicit activities or legal issues

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

    "to" followed by a verb of assistance

    np_acts-logits-general · gemini-2.0-flash

    aid or help or support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     χρήση
    -0.69
     Use
    -0.69
    Use
    -0.63
     utilisent
    -0.62
    use
    -0.61
     mať
    -0.59
     use
    -0.58
     useAuth
    -0.56
     StatelessWidget
    -0.55
    serializers
    -0.55
    POSITIVE LOGITS
     aid
    0.94
     help
    0.84
     support
    0.82
     assist
    0.81
     supplement
    0.81
     bolster
    0.77
     complement
    0.74
     enhance
    0.72
     boost
    0.70
     augment
    0.70
    Act Density 0.347%

    No Known Activations