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

    Neuronpedia

    INDEX
    Explanations

    ----------------

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beers
    -0.07
    Season
    -0.07
    Basically
    -0.07
    richText
    -0.07
     claimed
    -0.07
     Protocol
    -0.07
     fas
    -0.06
     piss
    -0.06
    visions
    -0.06
    omega
    -0.06
    POSITIVE LOGITS
     Barcl
    0.07
    �
    0.07
    ίζει
    0.06
    _reservation
    0.06
    EXPORT
    0.06
     "---
    0.06
    _Event
    0.06
    arde
    0.06
    (defvar
    0.06
    ctime
    0.06
    Act Density 0.006%

    No Known Activations