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

    Neuronpedia

    INDEX
    Explanations

    product reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occasionally
    -0.07
    転
    -0.06
    _attached
    -0.06
    洞
    -0.06
    โต
    -0.06
     të
    -0.06
    Ông
    -0.06
    every
    -0.06
     confronting
    -0.06
     Ethiopia
    -0.06
    POSITIVE LOGITS
    руд
    0.07
    roups
    0.07
    ("../../
    0.07
     nep
    0.06
    書館
    0.06
    هدف
    0.06
     prize
    0.06
    (ALOAD
    0.06
    jec
    0.06
    -"
    0.06
    Act Density 0.088%

    No Known Activations