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

    Neuronpedia

    INDEX
    Explanations

    people in roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    느
    -0.07
    арх
    -0.07
     conversation
    -0.07
    plt
    -0.07
    覺
    -0.07
     Algeria
    -0.07
    urrence
    -0.06
    阅
    -0.06
    Nej
    -0.06
    ály
    -0.06
    POSITIVE LOGITS
     WEB
    0.07
    *****
    0.06
    "":
    0.06
     seg
    0.06
     úrov
    0.06
    .forEach
    0.06
    �로
    0.06
    _$
    0.06
     --------
    0.06
    "\
    0.06
    Act Density 0.187%

    No Known Activations