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

    Neuronpedia

    INDEX
    Explanations

    play games, roles, or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fyp
    2.46
    uity
    2.29
    acij
    2.21
    љ
    2.19
    ParseException
    2.15
    الہ
    2.09
     ذر
    2.06
    olocation
    2.06
    acije
    2.03
    ្សែ
    2.03
    POSITIVE LOGITS
    ğa
    2.27
    SBP
    2.21
    thur
    2.16
    mier
    2.13
    罘
    2.09
     contexte
    2.08
    2.05
    es
    2.05
    2.02
    ∠
    2.02
    Act Density 0.426%

    No Known Activations