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

    Neuronpedia

    INDEX
    Explanations

    numbers and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sto
    0.48
     ro
    0.47
     accretion
    0.47
     gen
    0.46
     balls
    0.46
     incredibly
    0.45
     acc
    0.44
     churn
    0.43
     support
    0.42
     tre
    0.42
    POSITIVE LOGITS
    ૦
    0.71
    ″
    0.68
    ′,
    0.64
     અને
    0.63
    ૯
    0.63
     ಹಾಗೂ
    0.62
     ಅಥವಾ
    0.61
     หรือ
    0.61
    ૪
    0.60
    км
    0.60
    Act Density 0.527%

    No Known Activations