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

    Neuronpedia

    INDEX
    Explanations

    Documentation/Tutorials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nob
    -0.08
     â
    -0.07
    ોક
    -0.07
     lak
    -0.07
     loy
    -0.07
    loh
    -0.07
     nitr
    -0.07
     kosa
    -0.07
    ign
    -0.07
    -factor
    -0.07
    POSITIVE LOGITS
     Should
    0.09
     Although
    0.09
     Like
    0.09
     Situated
    0.09
     हालांकि
    0.09
    <ul
    0.08
     Traditionally
    0.08
     Perform
    0.08
     Will
    0.08
    (Optional
    0.08
    Act Density 0.081%

    No Known Activations