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

    Neuronpedia

    INDEX
    Explanations

    media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .↵↵↵↵
    -0.07
     cosine
    -0.07
     DS
    -0.07
     Jane
    -0.07
    _echo
    -0.06
    िस
    -0.06
     Selector
    -0.06
    .DisplayMember
    -0.06
     Allah
    -0.06
     Dove
    -0.06
    POSITIVE LOGITS
     Md
    0.07
    prak
    0.07
    .det
    0.06
    送料無料
    0.06
    ヌ
    0.06
     ‐
    0.06
    =p
    0.06
    М
    0.06
    臺
    0.06
    ению
    0.06
    Act Density 0.017%

    No Known Activations