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

    Neuronpedia

    INDEX
    Explanations

    Rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zu
    -0.07
    ELEMENT
    -0.07
     dusk
    -0.07
    务
    -0.07
    \uD
    -0.06
    azi
    -0.06
    cribes
    -0.06
    лист
    -0.06
     hoax
    -0.06
    Speaker
    -0.06
    POSITIVE LOGITS
     Slider
    0.07
     modelName
    0.07
    _HORIZONTAL
    0.07
    getConnection
    0.07
    .favorite
    0.06
    шел
    0.06
    .initialize
    0.06
    �
    0.06
    🆕
    0.06
    _CLOSE
    0.06
    Act Density 0.003%

    No Known Activations