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

    Neuronpedia

    INDEX
    Explanations

    #include and import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     runoff
    0.61
     aspiring
    0.60
    🏼
    0.59
     garner
    0.59
    🏻
    0.58
     ingrained
    0.58
     hungry
    0.56
     curtail
    0.56
    izing
    0.56
     untapped
    0.56
    POSITIVE LOGITS
    öp
    0.59
    /**
    0.55
    embangunan
    0.54
     Öncelikle
    0.54
    Audio
    0.54
    佲
    0.53
    /***/
    0.52
    פי
    0.52
    يكل
    0.52
    ܝܢ
    0.52
    Act Density 0.005%

    No Known Activations