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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Screens
    -0.08
     opens
    -0.07
    _STARTED
    -0.07
    樹
    -0.06
    >J
    -0.06
    ):(
    -0.06
     değil
    -0.06
    }],
    -0.06
    https
    -0.06
     Pages
    -0.06
    POSITIVE LOGITS
     Designer
    0.06
     mastery
    0.06
     POSIX
    0.06
    ै,
    0.06
    extra
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵
    0.06
     interceptor
    0.06
    /un
    0.06
    -call
    0.06
    iza
    0.06
    Act Density 0.065%

    No Known Activations