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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stores
    -0.07
    	System
    -0.07
    Exclusive
    -0.07
    sumer
    -0.07
    yu
    -0.07
    Canon
    -0.06
     TestCase
    -0.06
    apo
    -0.06
    िड
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    >>()
    0.07
    VOICE
    0.07
    ")).
    0.07
    )$/
    0.07
    outines
    0.06
    _DOT
    0.06
    INTERFACE
    0.06
     endanger
    0.06
    /*/
    0.06
     LOC
    0.06
    Act Density 0.018%

    No Known Activations