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

    Neuronpedia

    INDEX
    Explanations

    terms related to historical and social dynamics

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

    before parentheses or after prepositions

    np_acts-logits-general · gemini-2.0-flash

    challenge, mistrust, infection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    非常的
    -1.04
    Whilst
    -1.03
     Whilst
    -1.01
     dimana
    -0.93
     whilst
    -0.91
    十分的
    -0.89
     diatas
    -0.87
     данного
    -0.85
     hierbei
    -0.84
     içerisinde
    -0.83
    POSITIVE LOGITS
     freilich
    1.29
     offenbar
    0.86
     guère
    0.84
     :
    0.84
    WebElementEntity
    0.80
    Vidite
    0.78
    refour
    0.78
    TagMode
    0.76
     (;;)
    0.76
    ​—
    0.76
    Act Density 2.803%

    No Known Activations