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

    Neuronpedia

    INDEX
    Explanations

    depends on context or choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lanz
    1.04
     انقل
    0.98
     halftime
    0.95
     intento
    0.94
     adelant
    0.92
    毽
    0.91
    فرم
    0.89
     peels
    0.89
     estran
    0.88
     shameful
    0.88
    POSITIVE LOGITS
    depending
    2.17
     depending
    2.16
     depends
    2.15
     tergantung
    2.14
    depends
    2.04
    取决于
    2.02
     Depends
    1.97
     depende
    1.88
    Depends
    1.86
     bergantung
    1.80
    Act Density 0.610%

    No Known Activations