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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interceptor
    -0.07
     SVM
    -0.06
    ařilo
    -0.06
     火
    -0.06
     Disposable
    -0.06
    قم
    -0.06
     태
    -0.06
     GR
    -0.06
    wis
    -0.06
    _mov
    -0.06
    POSITIVE LOGITS
     RH
    0.07
    名稱
    0.06
    **:
    0.06
     Flavor
    0.06
     coquine
    0.06
     Stevens
    0.06
     الى
    0.06
     Steven
    0.06
     Recommend
    0.06
     والأ
    0.06
    Act Density 0.005%

    No Known Activations