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

    Neuronpedia

    INDEX
    Explanations

    Finally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ɧ
    -0.07
    Ṧ
    -0.07
    ou
    -0.07
     Kern
    -0.07
    ⅀
    -0.07
    ⊇
    -0.07
    Ӝ
    -0.07
     deber
    -0.07
     Shel
    -0.07
     shield
    -0.07
    POSITIVE LOGITS
     Locations
    0.08
    (",");↵
    0.08
    逮捕
    0.08
    能不能
    0.08
    unci
    0.08
    县长
    0.07
     segundo
    0.07
    Cancelar
    0.07
     чтобы
    0.07
     下午
    0.07
    Act Density 0.014%

    No Known Activations