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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -vesm
    -0.08
    +l
    -0.07
     рождения
    -0.07
    альные
    -0.07
    aremos
    -0.06
    법
    -0.06
    _IC
    -0.06
     Funktion
    -0.06
    Yii
    -0.06
    onyms
    -0.06
    POSITIVE LOGITS
     nghiên
    0.07
     соци
    0.07
    ření
    0.07
     chocolates
    0.06
    拥
    0.06
     pens
    0.06
     сон
    0.06
     فرزند
    0.05
    ')));↵
    0.05
     πριν
    0.05
    Act Density 0.050%

    No Known Activations