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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <<<
    -0.07
    PLUGIN
    -0.07
    irit
    -0.07
    서는
    -0.07
    ?page
    -0.06
    onden
    -0.06
     nine
    -0.06
    DETAIL
    -0.06
     '$
    -0.06
    .CreateTable
    -0.06
    POSITIVE LOGITS
    caps
    0.06
    case
    0.06
     target
    0.06
    -Trump
    0.06
    ByExample
    0.06
     _______,
    0.06
     irritation
    0.06
     aa
    0.06
     only
    0.06
     REPLACE
    0.06
    Act Density 0.045%

    No Known Activations