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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ners
    -0.07
    uro
    -0.07
    erval
    -0.07
    y
    -0.06
    iculos
    -0.06
    玻璃
    -0.06
    е
    -0.06
    璃
    -0.06
    ement
    -0.06
    ylum
    -0.06
    POSITIVE LOGITS
    Utility
    0.07
     Ein
    0.07
     ImmutableList
    0.07
    _ASSIGN
    0.07
    _my
    0.06
    _PERMISSION
    0.06
     accr
    0.06
     Urb
    0.06
    𫚭
    0.06
    'I
    0.06
    Act Density 0.095%

    No Known Activations