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

    Neuronpedia

    INDEX
    Explanations

    mentions of independent reviews or evaluations

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

    independent followed by specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geographie
    -0.49
     gemeint
    -0.41
     '\\;'
    -0.38
    ویژگی
    -0.37
     fréqu
    -0.36
     relieving
    -0.36
     løs
    -0.35
     acost
    -0.34
    houding
    -0.34
    Tracce
    -0.34
    POSITIVE LOGITS
     independent
    1.16
    independent
    1.06
    Independent
    1.02
     Independent
    1.02
     indépendante
    0.92
     independently
    0.90
    独立
    0.90
     INDEPENDENT
    0.90
     indépendant
    0.88
     independientes
    0.86
    Act Density 0.019%

    No Known Activations