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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -svg
    -0.07
    ı
    -0.06
     Browns
    -0.06
     jacket
    -0.06
     temsil
    -0.06
     painted
    -0.06
    Ny
    -0.06
    phrase
    -0.06
     mood
    -0.06
    archy
    -0.06
    POSITIVE LOGITS
    ська
    0.06
     считается
    0.06
     یعنی
    0.06
     σκο
    0.06
     condominium
    0.06
     собой
    0.06
     validated
    0.06
     було
    0.06
    ¯¯¯¯
    0.06
     مانند
    0.06
    Act Density 0.032%

    No Known Activations