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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     له
    -0.07
     výbě
    -0.07
    (ap
    -0.06
     commands
    -0.06
    ,…↵↵
    -0.06
    มากกว
    -0.06
    rias
    -0.06
    หนด
    -0.06
    *np
    -0.06
    ระหว
    -0.06
    POSITIVE LOGITS
    UILTIN
    0.06
    Multiple
    0.06
     archival
    0.06
    avelength
    0.06
    uisine
    0.06
     twists
    0.06
    يكي
    0.06
     GC
    0.06
    award
    0.06
     catalyst
    0.06
    Act Density 0.015%

    No Known Activations