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

    Neuronpedia

    INDEX
    Explanations

    sans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fullfile
    -0.07
     каждого
    -0.07
    ModelAttribute
    -0.07
    -profile
    -0.06
    	st
    -0.06
    米
    -0.06
     vue
    -0.06
     unreliable
    -0.06
     Explanation
    -0.06
     foot
    -0.06
    POSITIVE LOGITS
    ANS
    0.07
    ンズ
    0.07
    атор
    0.06
    (Vec
    0.06
    ANK
    0.06
    PS
    0.06
     irres
    0.06
    gens
    0.06
    _TLS
    0.06
    ycl
    0.06
    Act Density 0.153%

    No Known Activations