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

    Neuronpedia

    INDEX
    Explanations

    journeys and destinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ro
    -0.07
    taken
    -0.06
    /find
    -0.06
    _xpath
    -0.06
    ☌
    -0.06
    ገ
    -0.06
     metros
    -0.06
     gastro
    -0.06
    راد
    -0.06
    -defense
    -0.06
    POSITIVE LOGITS
     ElseIf
    0.08
     dari
    0.07
    SplitOptions
    0.07
    把
    0.07
     ebp
    0.07
    0.07
    ")↵
    0.06
    ')↵↵
    0.06
    짜
    0.06
     getchar
    0.06
    Act Density 0.172%

    No Known Activations