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

    Neuronpedia

    INDEX
    Explanations

    Test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Operation
    -0.07
    emplace
    -0.07
    Prom
    -0.06
     Кам
    -0.06
    ']->
    -0.06
     губ
    -0.06
    ，因
    -0.06
     Truman
    -0.06
     POW
    -0.06
    ocracy
    -0.06
    POSITIVE LOGITS
    .DE
    0.07
    _ER
    0.06
    ching
    0.06
    983
    0.06
    мп
    0.06
     ClassName
    0.06
    clc
    0.06
     Ре
    0.06
     serialized
    0.06
    weise
    0.06
    Act Density 0.000%

    No Known Activations