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

    Neuronpedia

    INDEX
    Explanations

    participated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fakültesi
    -0.06
    arness
    -0.06
     Você
    -0.06
    .hasClass
    -0.06
    TestingModule
    -0.06
    StateMachine
    -0.06
    _exception
    -0.06
    Audit
    -0.06
    .tom
    -0.06
     qw
    -0.06
    POSITIVE LOGITS
     evolved
    0.07
    Paid
    0.07
     utilized
    0.07
     stole
    0.07
     Paid
    0.07
    Seq
    0.06
     asset
    0.06
     file
    0.06
    ΑΝ
    0.06
     relates
    0.06
    Act Density 0.122%

    No Known Activations