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

    Neuronpedia

    INDEX
    Explanations

    Rak, cinnamon, return, Linguiça

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     şart
    0.43
    핳
    0.42
    atea
    0.41
    変
    0.40
    刺
    0.40
     প্রদর্শ
    0.40
     वेयर
    0.39
     puffy
    0.39
    واه
    0.38
    irable
    0.38
    POSITIVE LOGITS
     Rak
    0.43
    Rak
    0.43
     Total
    0.42
    loggedIn
    0.42
    getY
    0.40
     NR
    0.40
    Y
    0.40
     பின்ன
    0.40
     य
    0.39
    InnoDB
    0.39
    Act Density 0.001%

    No Known Activations