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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CHE
    -0.09
     Nast
    -0.08
     Кос
    -0.07
    CHE
    -0.07
     Matth
    -0.07
    tal
    -0.07
     Marche
    -0.07
    േ�
    -0.07
    _depend
    -0.07
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.12
     എന്നിവ
    0.10
     đều
    0.09
    そして
    0.09
     그리고
    0.09
     എന്നീ
    0.08
    —all
    0.08
     كلها
    0.08
     semuanya
    0.08
     모두
    0.07
    Act Density 0.120%
    No Known Activations