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

    Neuronpedia

    INDEX
    Explanations

    hypothesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reportedly
    -0.09
     tolle
    -0.09
    ાળો
    -0.08
    chief
    -0.08
    clearfix
    -0.08
     tricks
    -0.08
     fantastic
    -0.08
    -neck
    -0.08
     alku
    -0.08
     Gerald
    -0.08
    POSITIVE LOGITS
     hypothesis
    0.12
     hypoth
    0.12
     hypotheses
    0.10
     correlate
    0.09
     sufficiently
    0.08
     mindestens
    0.08
    Hyp
    0.08
     proposes
    0.08
     increasingly
    0.08
     것이다
    0.08
    Act Density 0.018%

    No Known Activations