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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classification
    -0.08
     transaction
    -0.08
     transactional
    -0.07
     trên
    -0.07
     dealings
    -0.07
     crisp
    -0.07
     комиссии
    -0.07
     courts
    -0.07
     architectural
    -0.07
     rú
    -0.07
    POSITIVE LOGITS
    Loop
    0.15
     continuously
    0.15
     daemon
    0.14
     indefinitely
    0.14
    _loop
    0.14
     monitoring
    0.14
     Loop
    0.13
     looping
    0.13
    loop
    0.13
    daemon
    0.13
    Act Density 0.015%

    No Known Activations