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

    Neuronpedia

    INDEX
    Explanations

    scientific data measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Associ
    -0.06
     isl
    -0.06
    [counter
    -0.06
    존
    -0.05
    ecial
    -0.05
     دوم
    -0.05
     Lev
    -0.05
    "If
    -0.05
     Aviation
    -0.05
    雲
    -0.05
    POSITIVE LOGITS
    _orig
    0.08
    appe
    0.07
     Đài
    0.07
     Rally
    0.07
    ried
    0.07
     artikel
    0.06
    /catalog
    0.06
    roduce
    0.06
    &type
    0.06
    'action
    0.06
    Act Density 0.001%

    No Known Activations