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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dispose
    -0.07
     להעביר
    -0.07
     disrespectful
    -0.07
    ބ
    -0.07
    turn
    -0.07
    %H
    -0.07
    Ted
    -0.07
    GLISH
    -0.07
     GSL
    -0.06
    Base
    -0.06
    POSITIVE LOGITS
    -hooks
    0.08
    什么呢
    0.07
     quilt
    0.07
    уг
    0.07
     głównie
    0.07
     "}↵
    0.07
    嘞
    0.07
    }`);↵
    0.07
     ellipt
    0.07
     vit
    0.07
    Act Density 0.001%

    No Known Activations