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

    Neuronpedia

    INDEX
    Explanations

    XIV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     [@
    -0.06
    Ale
    -0.06
     розви
    -0.06
    caf
    -0.06
    IMPORT
    -0.06
    -resources
    -0.06
     oleh
    -0.06
     해
    -0.06
    	wc
    -0.06
    POSITIVE LOGITS
     съ
    0.10
    .Binary
    0.07
    Bounds
    0.07
     veel
    0.06
     Pets
    0.06
     Amazing
    0.06
     powerful
    0.06
    SEC
    0.06
     sweat
    0.06
    ображ
    0.06
    Act Density 0.019%

    No Known Activations