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

    Neuronpedia

    INDEX
    Explanations

    Penalty spot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ReadInt
    -0.07
     так
    -0.07
    akh
    -0.07
    אפשר
    -0.06
    ]);
↵
↵
    -0.06
     subclasses
    -0.06
    已成为
    -0.06
     Grape
    -0.06
     Mechanical
    -0.06
     Von
    -0.06
    POSITIVE LOGITS
     wspóln
    0.07
    etting
    0.07
    acies
    0.07
    .tabControl
    0.07
     hipp
    0.06
     truthful
    0.06
    𝒅
    0.06
    _reporting
    0.06
    芝加
    0.06
    aming
    0.06
    Act Density 0.010%

    No Known Activations