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

    Neuronpedia

    INDEX
    Explanations

    ingredients/components lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﮎ
    -0.08
     vatandaş
    -0.07
    私立
    -0.07
    مناطق
    -0.07
     deserves
    -0.07
     dõ
    -0.07
    erala
    -0.07
    蔬
    -0.07
     seçim
    -0.07
     yık
    -0.06
    POSITIVE LOGITS
     CATEGORY
    0.07
     conference
    0.07
    SB
    0.07
    𝕂
    0.07
    全覆盖
    0.06
    NON
    0.06
    aine
    0.06
    Reflection
    0.06
     shield
    0.06
    延
    0.06
    Act Density 0.010%

    No Known Activations