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

    Neuronpedia

    INDEX
    Explanations

    submit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fly
    -0.06
     церкви
    -0.06
     Time
    -0.06
     Страна
    -0.06
     ----------------------------------------------------------------------↵
    -0.06
     tell
    -0.06
    (levels
    -0.06
     ringing
    -0.06
     coordinate
    -0.06
     lives
    -0.06
    POSITIVE LOGITS
     submitted
    0.09
    Submission
    0.08
     submit
    0.08
     Submit
    0.08
     Premier
    0.08
     tumblr
    0.07
     submission
    0.07
    ("%.
    0.07
     Survivor
    0.07
    DER
    0.07
    Act Density 0.016%

    No Known Activations