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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _st
    -0.07
    �
    -0.07
    oste
    -0.07
    .Update
    -0.07
     Myers
    -0.07
     algebra
    -0.07
     Ross
    -0.07
     underlying
    -0.07
     chloride
    -0.06
     Finish
    -0.06
    POSITIVE LOGITS
    obbled
    0.06
    .UNKNOWN
    0.06
    面積
    0.06
    dictionary
    0.06
    ictionaries
    0.06
     trấn
    0.06
    ?=.*
    0.06
    .parametrize
    0.06
    ="#">↵
    0.06
     siti
    0.06
    Act Density 0.012%

    No Known Activations