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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate naming or categorization

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

    Preceding a term or name

    np_acts-logits-general · gemini-2.0-flash

    is called or termed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سكانية
    -0.65
    ValueStyle
    -0.65
    aucune
    -0.59
     XNUMX
    -0.59
     OGS
    -0.59
    autres
    -0.58
     comets
    -0.58
    évaluateur
    -0.57
     Hopf
    -0.57
     Hege
    -0.57
    POSITIVE LOGITS
     “
    1.28
     "
    1.24
     ‘
    1.08
     simply
    0.97
     «
    0.96
     '
    0.94
     „
    0.92
     `
    0.83
     ”
    0.83
    之为
    0.81
    Act Density 0.170%

    No Known Activations