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

    Neuronpedia

    INDEX
    Explanations

    First-person narrative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gb
    -0.07
    罚
    -0.07
     manuscript
    -0.06
     radios
    -0.06
    ordination
    -0.06
     attic
    -0.06
     Kub
    -0.06
    зації
    -0.06
    cludes
    -0.06
    153
    -0.06
    POSITIVE LOGITS
    .Packet
    0.07
     nějak
    0.07
     vyvol
    0.07
     �
    0.06
    rich
    0.06
    łu
    0.06
     Дем
    0.06
    (IN
    0.06
    에서는
    0.06
    では
    0.06
    Act Density 0.104%

    No Known Activations