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

    Neuronpedia

    INDEX
    Explanations

    ruby code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нами
    0.42
    putString
    0.42
     লক্ষ
    0.41
    omas
    0.39
     भि
    0.39
     compter
    0.39
    ྃ
    0.39
     toma
    0.37
     comté
    0.37
    榔
    0.37
    POSITIVE LOGITS
     def
    0.64
    def
    0.64
    attr
    0.55
    救援
    0.50
     include
    0.50
    include
    0.50
     Include
    0.50
    rescue
    0.47
    unload
    0.47
     Def
    0.46
    Act Density 0.000%

    No Known Activations