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

    Neuronpedia

    INDEX
    Explanations

    .Collections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iba
    -0.07
    .detail
    -0.07
     дії
    -0.06
     Reign
    -0.06
     Yu
    -0.06
    Local
    -0.06
     Lump
    -0.06
    Va
    -0.06
     classifications
    -0.06
    RIGHT
    -0.06
    POSITIVE LOGITS
    cas
    0.07
    อค
    0.07
    ียรต
    0.06
    (DBG
    0.06
    ế
    0.06
     Join
    0.06
    _OPERATION
    0.06
     (_.
    0.06
     masters
    0.06
    ọt
    0.06
    Act Density 0.001%

    No Known Activations