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

    Neuronpedia

    INDEX
    Explanations

    terms related to language translation and resources for contributors

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

    translate and interpret language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vivienda
    -0.39
     geométrico
    -0.39
     suun
    -0.37
    挙
    -0.37
    AnimationsModule
    -0.37
     MUNICIPAL
    -0.36
    劝
    -0.36
    sho
    -0.36
     femenina
    -0.36
     הנו
    -0.36
    POSITIVE LOGITS
    tangentMode
    0.47
     Signalez
    0.44
    AutoScaleMode
    0.44
    々木
    0.44
     CIE
    0.43
    BorderFactory
    0.42
     Catawiki
    0.42
    ChrTalk
    0.42
    scryfall
    0.41
     Linguistics
    0.41
    Act Density 0.006%

    No Known Activations