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

    Neuronpedia

    INDEX
    Explanations

    website

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -national
    -0.07
    _ctrl
    -0.07
    마트
    -0.07
    싸
    -0.07
    erd
    -0.06
     soutěže
    -0.06
    Vien
    -0.06
    sts
    -0.06
     Wald
    -0.06
    르
    -0.06
    POSITIVE LOGITS
     retrieving
    0.07
    �니다
    0.06
    .beta
    0.06
     comes
    0.06
     min
    0.06
     apolog
    0.06
     explan
    0.06
     الخارج
    0.06
    _BT
    0.06
     violet
    0.06
    Act Density 0.011%

    No Known Activations