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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tảng
    -0.06
     dür
    -0.06
    üns
    -0.06
    Aside
    -0.06
    pendicular
    -0.06
    otoxic
    -0.06
    ThanOr
    -0.06
     Evet
    -0.06
     Along
    -0.06
    ीण
    -0.06
    POSITIVE LOGITS
     oxidation
    0.08
    mode
    0.08
    Sy
    0.07
    ))))↵↵
    0.07
    ]))
    0.07
     پي
    0.06
    رفت
    0.06
     Oper
    0.06
     nhạc
    0.06
    .exec
    0.06
    Act Density 0.000%

    No Known Activations