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

    Neuronpedia

    INDEX
    Explanations

    Ang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旞
    -0.07
     supplied
    -0.07
     variable
    -0.07
    本能
    -0.07
    נדר
    -0.07
    sync
    -0.06
    靽
    -0.06
     facet
    -0.06
     proof
    -0.06
    repid
    -0.06
    POSITIVE LOGITS
     אותן
    0.08
    -dominated
    0.08
     오히려
    0.07
    .rt
    0.07
     לפעמים
    0.07
     studying
    0.07
     alan
    0.07
     threatens
    0.07
     revolves
    0.07
     mocks
    0.07
    Act Density 0.035%

    No Known Activations