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

    Neuronpedia

    INDEX
    Explanations

    medium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原本
    -0.07
     precip
    -0.07
    cosity
    -0.07
    (transform
    -0.07
     coz
    -0.07
    import
    -0.07
    бе
    -0.07
    汽车
    -0.06
     Dank
    -0.06
    MaxLength
    -0.06
    POSITIVE LOGITS
     LO
    0.07
     jeans
    0.06
     (:
    0.06
     stocks
    0.06
     jit
    0.06
     lament
    0.06
     (::
    0.06
     WS
    0.06
    Ljava
    0.05
     verm
    0.05
    Act Density 0.004%

    No Known Activations