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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something being exceptionally good or enjoyable

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

    too X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insuffisamment
    -0.52
    ніципа
    -0.47
    الحياه
    -0.44
    }]
    -0.44
    ſelves
    -0.44
     Perſ
    -0.43
    +#+#
    -0.43
     testSet
    -0.43
    دانشنامهٔ
    -0.42
    }],
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.43
    appartamento
    0.41
    occasione
    0.40
    ujudkan
    0.39
     miraculous
    0.39
    KommentareTeilen
    0.38
    accesso
    0.37
     devastating
    0.35
    SharedCtor
    0.35
     Utilize
    0.34
    Act Density 0.005%

    No Known Activations