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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “All
    -0.07
    Survey
    -0.07
    Hang
    -0.06
    "All
    -0.06
     bureaucratic
    -0.06
    Anal
    -0.06
    /styles
    -0.06
     COLLECTION
    -0.06
     Κου
    -0.06
    _COLL
    -0.06
    POSITIVE LOGITS
     sangat
    0.07
    олі
    0.06
     ﾚ
    0.06
    ns
    0.06
    ned
    0.06
    (message
    0.06
     sms
    0.06
    ुह
    0.06
    ород
    0.06
     bel
    0.06
    Act Density 0.016%

    No Known Activations