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

    Neuronpedia

    INDEX
    Explanations

    Size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invoices
    -0.08
    (private
    -0.07
    寒冷
    -0.07
    utowired
    -0.07
    澧
    -0.07
     external
    -0.07
    _ctrl
    -0.06
     vừa
    -0.06
    lections
    -0.06
    豪华
    -0.06
    POSITIVE LOGITS
     cds
    0.07
     Tara
    0.07
     percentage
    0.07
     programa
    0.07
     cs
    0.07
     ByteArray
    0.07
     remake
    0.07
     BYTE
    0.07
     רבה
    0.07
     ELF
    0.06
    Act Density 0.001%

    No Known Activations