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

    Neuronpedia

    INDEX
    Explanations

    stories and jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enables
    -0.06
    ata
    -0.06
     olig
    -0.06
    альном
    -0.06
     permitted
    -0.06
     benefits
    -0.06
     mommy
    -0.06
     QVERIFY
    -0.06
     folk
    -0.06
    Confirmation
    -0.06
    POSITIVE LOGITS
    .stub
    0.07
    (金
    0.07
    求
    0.07
     bitte
    0.07
    شان
    0.07
    _action
    0.06
    .links
    0.06
     proph
    0.06
     SizedBox
    0.06
    [email
    0.06
    Act Density 0.043%

    No Known Activations