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

    Neuronpedia

    INDEX
    Explanations

    capabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Invalid
    -0.07
     Disqus
    -0.06
     집
    -0.06
     Rohingya
    -0.06
     некотор
    -0.06
     jogo
    -0.06
    Pixel
    -0.06
    PWM
    -0.06
     Р
    -0.06
    Pri
    -0.06
    POSITIVE LOGITS
    erness
    0.07
     feelings
    0.07
    /widgets
    0.06
     vows
    0.06
    اعر
    0.06
     默认
    0.06
     abilities
    0.06
    urat
    0.06
     aesthetics
    0.06
    或者
    0.06
    Act Density 0.359%

    No Known Activations