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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ،↵
    -0.07
     mechanic
    -0.07
    níka
    -0.07
     absorb
    -0.07
    .NODE
    -0.06
    _DEAD
    -0.06
    -_
    -0.06
     Wow
    -0.06
    ↵↵↵
    -0.06
    Wow
    -0.06
    POSITIVE LOGITS
     groupBox
    0.07
     เ�
    0.07
    CLK
    0.07
     Bulldogs
    0.06
    λέ
    0.06
     og
    0.06
    SError
    0.06
    Ev
    0.06
     Klo
    0.06
    ορ
    0.06
    Act Density 0.045%

    No Known Activations