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

    Neuronpedia

    INDEX
    Explanations

    cur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HEAD
    -0.07
     SSD
    -0.07
     displ
    -0.07
    [idx
    -0.06
     €
    -0.06
    .addEventListener
    -0.06
    Millis
    -0.06
    _lock
    -0.06
    ンブ
    -0.06
     shattered
    -0.06
    POSITIVE LOGITS
     gerçekleştir
    0.07
     Nẵng
    0.06
    ，上
    0.06
     CIM
    0.06
    λευτα
    0.06
    verbose
    0.06
    Observers
    0.06
    ّة
    0.06
    797
    0.06
    -cat
    0.06
    Act Density 0.001%

    No Known Activations