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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahaha
    -0.07
     çünkü
    -0.07
     artery
    -0.06
    чила
    -0.06
     dever
    -0.06
    <TEntity
    -0.06
    estro
    -0.06
     запрос
    -0.06
     wrestling
    -0.06
     denotes
    -0.06
    POSITIVE LOGITS
    Mgr
    0.07
    MAT
    0.07
    att
    0.06
    �
    0.06
     ngoài
    0.06
     famine
    0.06
    oài
    0.06
     نام
    0.06
     山
    0.06
    住
    0.06
    Act Density 0.677%

    No Known Activations