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

    Neuronpedia

    INDEX
    Explanations

    Code/Math/Lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    циальн
    -0.08
    Simply
    -0.07
    icycle
    -0.07
    mur
    -0.07
    باس
    -0.07
    VL
    -0.07
     bury
    -0.07
    低温
    -0.07
    �
    -0.07
    猫咪
    -0.07
    POSITIVE LOGITS
    **↵
    0.07
    _called
    0.07
    ('#
    0.07
    >(&
    0.07
     Within
    0.07
    ={`
    0.07
    ']=='
    0.07
    =top
    0.06
     pobliżu
    0.06
    ->{_
    0.06
    Act Density 0.000%

    No Known Activations