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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сад
    -0.06
    (rb
    -0.06
     Guarantee
    -0.06
    .ComponentPlacement
    -0.06
    Mod
    -0.06
     NES
    -0.06
     hỗ
    -0.06
    좀
    -0.06
     pharmacist
    -0.06
     precondition
    -0.06
    POSITIVE LOGITS
     NOT
    0.07
    nummer
    0.06
     Who
    0.06
    =row
    0.06
     Nos
    0.06
    .Microsoft
    0.06
    _PATTERN
    0.06
     Petra
    0.06
     Imam
    0.06
     Τα
    0.06
    Act Density 0.000%

    No Known Activations