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

    Neuronpedia

    INDEX
    Explanations

    Lessons learned/takeaways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zosta
    -0.07
     intellect
    -0.07
    [Test
    -0.07
     Film
    -0.07
     emerging
    -0.07
     Epoch
    -0.07
     USED
    -0.07
    为您提供
    -0.06
     staunch
    -0.06
    inema
    -0.06
    POSITIVE LOGITS
    슨
    0.08
    뇽
    0.07
    пит
    0.07
     crude
    0.07
    威廉
    0.06
     Tories
    0.06
    _clr
    0.06
     AUD
    0.06
    𬬩
    0.06
     louis
    0.06
    Act Density 0.053%

    No Known Activations