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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    windows
    -0.07
    _micro
    -0.07
    Rightarrow
    -0.07
    üyoruz
    -0.06
    steam
    -0.06
    Unix
    -0.06
     weeds
    -0.06
    postgres
    -0.06
     ICE
    -0.06
     француз
    -0.06
    POSITIVE LOGITS
     tipping
    0.07
     المن
    0.07
    Wy
    0.07
    えた
    0.07
    -disable
    0.07
    방
    0.07
     živ
    0.06
    _idle
    0.06
    不到
    0.06
    译
    0.06
    Act Density 0.082%

    No Known Activations