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

    Neuronpedia

    INDEX
    Explanations

    references to films, specifically mentioning directors and associated works

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quoted titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hibli
    -0.70
     Pols
    -0.67
    Portály
    -0.66
     contextLoads
    -0.63
    CrossRef
    -0.61
    Slayer
    -0.58
     honte
    -0.58
    下载附件
    -0.57
     âgé
    -0.56
     hâte
    -0.56
    POSITIVE LOGITS
     The
    0.75
     entitled
    0.62
     titled
    0.58
     A
    0.56
    The
    0.56
     Winaray
    0.54
    üyada
    0.54
     nakalista
    0.54
     ModelExpression
    0.51
     All
    0.50
    Act Density 0.143%

    No Known Activations