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

    Neuronpedia

    INDEX
    Explanations

    learning and science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٬
    1.05
    ബരിമല
    1.02
    Obes
    1.02
    1.02
    1.02
     Генера
    1.01
    ар
    1.00
    ‌,
    1.00
    
    1.00
    
    0.98
    POSITIVE LOGITS
     basil
    0.97
     latte
    0.97
     metric
    0.95
     equations
    0.95
     emulsion
    0.95
     emoji
    0.93
     sache
    0.93
     thermodynamics
    0.93
     was
    0.92
     aspen
    0.92
    Act Density 0.170%

    No Known Activations