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

    Neuronpedia

    INDEX
    Explanations

    brackets and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    佩
    -0.06
    Evidence
    -0.06
    emos
    -0.06
     boil
    -0.06
    _CONN
    -0.06
    /js
    -0.06
     boasting
    -0.06
    EDIUM
    -0.06
     counties
    -0.06
    783
    -0.06
    POSITIVE LOGITS
    ุน
    0.08
    佛
    0.06
     ई
    0.06
    ,request
    0.06
    ';';
    0.06
    рог
    0.06
    NASA
    0.06
     pepp
    0.06
    чина
    0.06
    ...'
    0.06
    Act Density 0.376%

    No Known Activations