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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     숙
    -0.07
    би
    -0.06
    ип
    -0.06
    SID
    -0.06
     backend
    -0.06
    .bottomAnchor
    -0.06
     Dick
    -0.06
     Krish
    -0.06
    знача
    -0.06
    沈
    -0.06
    POSITIVE LOGITS
    (newUser
    0.07
     Administrative
    0.06
    ��
    0.06
    iveau
    0.06
     Ping
    0.06
    .pagination
    0.06
    pping
    0.06
     breaks
    0.06
     Public
    0.06
     exploring
    0.06
    Act Density 0.003%

    No Known Activations