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

    Neuronpedia

    INDEX
    Explanations

    legal context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UG
    -0.06
    phase
    -0.06
    _bar
    -0.06
     toll
    -0.06
    _PLUS
    -0.06
    /block
    -0.06
     collaboration
    -0.06
     suggesting
    -0.06
     查
    -0.06
     scraped
    -0.05
    POSITIVE LOGITS
     sax
    0.07
     odstran
    0.07
     inh
    0.07
     직접
    0.07
    .GraphicsUnit
    0.07
     Genel
    0.07
     самым
    0.06
    DockControl
    0.06
     любов
    0.06
     UserProfile
    0.06
    Act Density 0.009%

    No Known Activations