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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Major
    -0.07
     להיכ
    -0.06
     bunk
    -0.06
     Leaves
    -0.06
     transformers
    -0.06
    .SetValue
    -0.06
     Suite
    -0.06
    这也是
    -0.06
     mower
    -0.06
     Toyota
    -0.06
    POSITIVE LOGITS
    /she
    0.07
    _groups
    0.07
    !↵↵
    0.07
    icals
    0.07
    فرق
    0.07
     rap
    0.06
    urities
    0.06
    (GameObject
    0.06
    ,");↵
    0.06
    不必要的
    0.06
    Act Density 0.113%

    No Known Activations