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

    Neuronpedia

    INDEX
    Explanations

    actions related to decision-making and selection processes

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

    introducing or detailing specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.63
    tagHelperRunner
    -0.56
    səhifə
    -0.52
     weiterer
    -0.49
     betreffenden
    -0.48
     tästä
    -0.48
     Administrativna
    -0.48
     незавершена
    -0.47
     mauva
    -0.47
     verschill
    -0.44
    POSITIVE LOGITS
    :
    0.56
    的是
    0.47
     namely
    0.45
    namely
    0.45
     Fra
    0.44
    のが
    0.43
     including
    0.43
     besides
    0.42
    besides
    0.42
     include
    0.41
    Act Density 0.144%

    No Known Activations