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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کاری
    -0.07
     що
    -0.06
     são
    -0.06
    (member
    -0.06
     Licensed
    -0.06
     nüfus
    -0.06
    (total
    -0.06
    _CHANGE
    -0.06
    坂
    -0.06
    Location
    -0.06
    POSITIVE LOGITS
     ciphertext
    0.08
    ique
    0.07
     Existing
    0.06
     Schwar
    0.06
    ave
    0.06
     향
    0.06
     Aerospace
    0.06
     Swing
    0.06
    Never
    0.06
     independents
    0.06
    Act Density 0.006%

    No Known Activations