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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    说
    -0.08
     имеет
    -0.07
    .Save
    -0.07
    做
    -0.07
     coming
    -0.06
    from
    -0.06
    (F
    -0.06
     filled
    -0.06
     nerd
    -0.06
    ，说
    -0.06
    POSITIVE LOGITS
     bedside
    0.09
     bishop
    0.08
    ró
    0.07
     Radio
    0.07
    اج
    0.07
     beside
    0.07
     alongside
    0.07
    UEST
    0.07
     Bij
    0.07
    řen
    0.06
    Act Density 0.014%

    No Known Activations