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

    Neuronpedia

    INDEX
    Explanations

    positive qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kor
    -0.07
     m
    -0.06
    ox
    -0.06
    كيل
    -0.06
    Super
    -0.06
     mutants
    -0.06
    rum
    -0.06
    rz
    -0.06
     citizen
    -0.06
    (ST
    -0.06
    POSITIVE LOGITS
    .createElement
    0.07
     sahibi
    0.07
    rganization
    0.06
    library
    0.06
    IMPLEMENT
    0.06
    izing
    0.06
     reliability
    0.06
    แหน
    0.06
     inertia
    0.06
    思い
    0.06
    Act Density 0.102%

    No Known Activations