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

    Neuronpedia

    INDEX
    Explanations

    code imports and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.35
     GaAs
    0.34
    .)
    0.34
     의한
    0.33
     NaN
    0.33
    )
    0.32
    ?)
    0.31
     влияет
    0.31
     נ
    0.31
    <0x11>
    0.31
    POSITIVE LOGITS
    Utils
    0.37
    constraintlayout
    0.36
    倞
    0.35
    两个人
    0.34
    utils
    0.33
     ▪
    0.33
    interfaces
    0.33
    components
    0.32
    䅧
    0.32
    config
    0.31
    Act Density 0.001%

    No Known Activations