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

    Neuronpedia

    INDEX
    Explanations

    instances related to rewards or incentives for support

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

    Benefits or rewards for membership or purchase

    np_acts-logits-general · gemini-2.0-flash

    exclusive access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.70
    theless
    -0.68
     فريبيس
    -0.62
    Pautan
    -0.61
    archiviato
    -0.60
     defaultstate
    -0.58
     hefyd
    -0.58
    tanleria
    -0.57
    disfraz
    -0.56
     denominator
    -0.56
    POSITIVE LOGITS
     exclusive
    1.16
     access
    1.03
     EXCLUSIVE
    0.98
    Exclusive
    0.94
    exclusive
    0.91
     unlimited
    0.89
     accès
    0.89
     Exclusive
    0.88
     eksklu
    0.88
     exklu
    0.84
    Act Density 0.185%

    No Known Activations