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

    Neuronpedia

    INDEX
    Explanations

    how things are done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ることができます
    0.47
     Prevalence
    0.46
    λε
    0.46
    ली
    0.44
    としても
    0.44
    だけでも
    0.43
     lors
    0.42
     optimally
    0.42
     prevalence
    0.42
     possiamo
    0.42
    POSITIVE LOGITS
     obsess
    0.46
    方法
    0.45
     focussing
    0.43
    methods
    0.42
     décou
    0.42
    method
    0.42
    reliance
    0.41
     obsession
    0.40
     키
    0.40
     style
    0.39
    Act Density 0.021%

    No Known Activations