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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Torch
    -0.06
    ,key
    -0.06
    بیر
    -0.06
     매우
    -0.06
     fullscreen
    -0.06
     kiến
    -0.06
     dikkat
    -0.06
    write
    -0.06
     casually
    -0.06
    Scale
    -0.06
    POSITIVE LOGITS
     GetType
    0.06
    Inspectable
    0.06
    charAt
    0.06
    \models
    0.06
    lesh
    0.06
    pdata
    0.06
     BASE
    0.06
     Putin
    0.06
    })(
    0.06
     distint
    0.06
    Act Density 0.008%

    No Known Activations