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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     البي
    -0.07
     whispered
    -0.07
     المش
    -0.06
    叶
    -0.06
     ngọt
    -0.06
    'es
    -0.06
     sanctuary
    -0.06
     coz
    -0.06
     Meh
    -0.06
     каш
    -0.06
    POSITIVE LOGITS
     grades
    0.07
    edited
    0.06
    слов
    0.06
    	update
    0.06
    Listening
    0.06
    imiters
    0.06
    /G
    0.06
     Radical
    0.06
    _finalize
    0.06
    SFML
    0.06
    Act Density 0.000%

    No Known Activations