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

    Neuronpedia

    INDEX
    Explanations

    cumulative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    filename
    -0.07
    쌩
    -0.07
    괜
    -0.07
    -too
    -0.06
     elementary
    -0.06
    MAND
    -0.06
    Ol
    -0.06
     Beginners
    -0.06
     Greeks
    -0.06
     gost
    -0.06
    POSITIVE LOGITS
     Meeting
    0.08
    ']."
    0.08
    _POST
    0.07
    ープ
    0.07
    惶
    0.07
    (card
    0.07
    旗帜
    0.07
     pressured
    0.07
    onta
    0.06
     NUMBER
    0.06
    Act Density 0.015%

    No Known Activations