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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ให
    -0.07
     MEMBER
    -0.07
    addr
    -0.06
     wiped
    -0.06
     DD
    -0.06
    app
    -0.06
     بیرون
    -0.06
    Write
    -0.06
    암
    -0.06
    อให
    -0.06
    POSITIVE LOGITS
     fj
    0.07
    "]=$
    0.07
    Lou
    0.06
     berk
    0.06
     allegations
    0.06
    \v
    0.06
    ��
    0.06
    .connector
    0.06
    qv
    0.06
    g
    0.06
    Act Density 0.010%

    No Known Activations