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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    惕
    -0.07
    Coefficient
    -0.07
     Defendants
    -0.07
     precedence
    -0.07
    🔽
    -0.06
    モデル
    -0.06
    .SetActive
    -0.06
     overhead
    -0.06
     Sunshine
    -0.06
    ڑ
    -0.06
    POSITIVE LOGITS
    iasm
    0.09
    是他
    0.08
     inbox
    0.08
     italiano
    0.07
    ฐ
    0.07
    GBK
    0.07
    מערכות
    0.07
    .realpath
    0.07
    𐤏
    0.07
    _ITER
    0.07
    Act Density 0.017%

    No Known Activations