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

    Neuronpedia

    INDEX
    Explanations

    shave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عنها
    -0.08
    logic
    -0.08
     reasonably
    -0.07
    ↵        ↵
    -0.07
    From
    -0.07
     thematic
    -0.07
     أيضا
    -0.07
    Gener
    -0.07
    Keyword
    -0.07
     أيضًا
    -0.07
    POSITIVE LOGITS
     Copper
    0.08
    שרת
    0.08
    irond
    0.08
     pistol
    0.08
     vzd
    0.08
     платформ
    0.08
    .proto
    0.08
     двум
    0.08
    ярод
    0.08
    ущества
    0.08
    Act Density 0.000%

    No Known Activations