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

    Neuronpedia

    INDEX
    Explanations

    Choosing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pending
    -0.07
    sx
    -0.07
     vite
    -0.06
    URATION
    -0.06
     IS
    -0.06
    .ns
    -0.06
    ne
    -0.06
     Suite
    -0.06
     aspiration
    -0.06
     mercenaries
    -0.06
    POSITIVE LOGITS
     làn
    0.07
     bát
    0.07
    aec
    0.07
    ्वर
    0.06
    .Receive
    0.06
     ConfigurationManager
    0.06
    aded
    0.06
     Sanity
    0.06
     ı
    0.06
    สาม
    0.06
    Act Density 0.034%

    No Known Activations