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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pired
    -0.07
     ảnh
    -0.07
    褲
    -0.07
    Most
    -0.07
    vc
    -0.07
    ICLE
    -0.06
    (http
    -0.06
    CLE
    -0.06
    /python
    -0.06
    基于
    -0.06
    POSITIVE LOGITS
    _Flag
    0.07
    tör
    0.07
    imits
    0.07
    _change
    0.07
    ancellable
    0.06
    bla
    0.06
    _VARS
    0.06
     lowered
    0.06
     volleyball
    0.06
     finalized
    0.06
    Act Density 0.005%

    No Known Activations