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

    Neuronpedia

    INDEX
    Explanations

    rot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мира
    -0.07
     Chern
    -0.07
    Elite
    -0.07
     robes
    -0.07
     Grain
    -0.06
    лия
    -0.06
     Blade
    -0.06
    če
    -0.06
    ibe
    -0.06
    ／/
    -0.06
    POSITIVE LOGITS
    rots
    0.07
     LinkedIn
    0.06
     Aws
    0.06
    	f
    0.06
     NSF
    0.06
     выс
    0.06
    otate
    0.06
    ADED
    0.06
     protect
    0.06
     praying
    0.06
    Act Density 0.002%

    No Known Activations