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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Super
    -0.08
    Super
    -0.07
    人人
    -0.07
    ♐
    -0.07
     acceptable
    -0.07
    selectors
    -0.07
     amusement
    -0.07
    .canvas
    -0.07
    相关的
    -0.07
    subclass
    -0.07
    POSITIVE LOGITS
    ട
    0.07
    اة
    0.07
    刈
    0.07
     giận
    0.06
    ورية
    0.06
     yap
    0.06
    ∜
    0.06
    风吹
    0.06
    hire
    0.06
    损坏
    0.06
    Act Density 0.035%

    No Known Activations