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

    Neuronpedia

    INDEX
    Explanations

    references to web-related topics and information management

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

    Followed by a proper noun

    np_acts-logits-general · gemini-2.0-flash

    information on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     démocr
    -0.69
     réguli
    -0.66
     nacer
    -0.55
     regulares
    -0.55
     complètes
    -0.55
     väli
    -0.54
     myö
    -0.54
     tranquille
    -0.53
     kasarigan
    -0.53
     lunak
    -0.53
    POSITIVE LOGITS
     how
    1.77
     why
    1.45
    如何
    1.17
     cómo
    1.14
     whether
    1.13
     what
    1.13
     نحوه
    1.10
    how
    1.10
     hvordan
    1.02
     possible
    1.01
    Act Density 0.594%

    No Known Activations