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

    Neuronpedia

    INDEX
    Explanations

    continue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erit
    1.25
    erà
    1.16
    臾
    1.11
     deleteAll
    1.11
     traduire
    1.10
    o
    1.07
    cional
    1.06
     radica
    1.05
     arrête
    1.05
     afford
    1.05
    POSITIVE LOGITS
     पाण्डे
    1.08
    ভি
    1.06
    ಿಗೆ
    1.03
    ype
    1.00
    ogether
    1.00
    Patterns
    0.99
     Ove
    0.99
    वि
    0.99
    Phosph
    0.99
    ς
    0.99
    Act Density 0.000%

    No Known Activations