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

    Neuronpedia

    INDEX
    Explanations

    fantastical, cold elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    خی
    -0.07
    /I
    -0.07
    917
    -0.07
     học
    -0.07
    学院
    -0.07
     Ninh
    -0.07
     Sanford
    -0.06
     walls
    -0.06
     ngoài
    -0.06
    巧
    -0.06
    POSITIVE LOGITS
     assess
    0.07
    -relative
    0.06
    ');↵↵↵↵
    0.06
     Veteran
    0.06
     babes
    0.06
    favorite
    0.06
    ="">
↵
    0.06
    (gui
    0.06
    .detectChanges
    0.06
    master
    0.06
    Act Density 0.078%

    No Known Activations