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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truncated
    -0.07
     fayd
    -0.06
     حسب
    -0.06
     saldırı
    -0.06
     рабо
    -0.06
     guidelines
    -0.06
     Shader
    -0.06
    _REQUIRED
    -0.06
     countered
    -0.06
    lacağı
    -0.06
    POSITIVE LOGITS
    //---------------------------------------------------------------------------↵↵
    0.07
     gboolean
    0.07
    itle
    0.07
    '];?>↵
    0.07
    onyms
    0.06
     betray
    0.06
    	Connection
    0.06
     Tome
    0.06
    >";↵↵
    0.06
     реж
    0.06
    Act Density 0.036%

    No Known Activations