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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to food items and their categorization

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

    kebabs and Japanese reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    into
    -0.45
    Into
    -0.44
     Manusia
    -0.44
     Lainnya
    -0.43
     Gubernur
    -0.43
     Gór
    -0.42
     Espanha
    -0.42
     monasterio
    -0.41
     Polri
    -0.40
     Internasional
    -0.40
    POSITIVE LOGITS
     Keb
    1.07
    Keb
    0.99
     keb
    0.87
    __.__
    0.77
     од
    0.76
     يتيمه
    0.71
     müſſen
    0.65
     wiſſen
    0.64
    ระ
    0.64
     verſch
    0.62
    Act Density 0.003%

    No Known Activations