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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    افر
    -0.06
    Advanced
    -0.06
    	sign
    -0.06
    (help
    -0.06
    Easy
    -0.06
     highlights
    -0.06
     Tate
    -0.06
     easy
    -0.06
    šil
    -0.06
    _STATIC
    -0.06
    POSITIVE LOGITS
    >Password
    0.08
     đo
    0.07
    })↵↵
    0.06
    mue
    0.06
    劉
    0.06
    der
    0.06
     oste
    0.06
     Zhu
    0.06
    /foo
    0.06
     SME
    0.06
    Act Density 0.105%

    No Known Activations