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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reacting
    -0.07
     북
    -0.07
     Goodman
    -0.07
    Broad
    -0.07
    萩
    -0.07
    (DateTime
    -0.07
    Ƭ
    -0.07
    SeekBar
    -0.06
    小白
    -0.06
     fit
    -0.06
    POSITIVE LOGITS
     Religion
    0.07
    作息
    0.07
     elabor
    0.07
     operations
    0.07
    .rpc
    0.07
     machines
    0.07
    惟
    0.06
     desired
    0.06
    公安局
    0.06
     Rules
    0.06
    Act Density 0.001%

    No Known Activations