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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =current
    -0.07
     못
    -0.06
     Lopez
    -0.06
    崎
    -0.06
    _BOX
    -0.06
    $scope
    -0.06
     查
    -0.06
    +
    -0.06
    보험
    -0.06
    قل
    -0.06
    POSITIVE LOGITS
     PROCUREMENT
    0.07
     wie
    0.07
    _phi
    0.06
    ující
    0.06
    _kill
    0.06
     slime
    0.06
    (selector
    0.06
    现在
    0.06
     protester
    0.06
     looping
    0.06
    Act Density 0.001%

    No Known Activations