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

    Neuronpedia

    INDEX
    Explanations

    80

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slips
    -0.06
     jerk
    -0.06
    Handled
    -0.06
    nya
    -0.06
    áhl
    -0.06
    قدر
    -0.06
    Changing
    -0.06
    charted
    -0.06
    �
    -0.06
    心
    -0.06
    POSITIVE LOGITS
     fluorescent
    0.07
    -posts
    0.07
     steward
    0.07
    \Config
    0.07
    tein
    0.07
    нес
    0.07
     элек
    0.06
    /rss
    0.06
     evangelical
    0.06
    apeut
    0.06
    Act Density 0.000%

    No Known Activations