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

    Neuronpedia

    INDEX
    Explanations

    engine oil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    March
    -0.07
     NV
    -0.07
    (coordinates
    -0.06
    binding
    -0.06
    ruk
    -0.06
     March
    -0.06
    gow
    -0.06
     scaled
    -0.06
     Fargo
    -0.06
    ταν
    -0.06
    POSITIVE LOGITS
     От
    0.07
     afterEach
    0.07
     př
    0.06
     Anth
    0.06
    _trees
    0.06
     Including
    0.06
     princip
    0.06
    )didReceiveMemoryWarning
    0.06
     UserControl
    0.05
    /orders
    0.05
    Act Density 0.010%

    No Known Activations