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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ріп
    -0.07
     wrest
    -0.06
    ู้
    -0.06
     kuk
    -0.06
    _macro
    -0.06
     Inst
    -0.06
    ゆ
    -0.06
     ø
    -0.06
    Inst
    -0.06
    POSITIVE LOGITS
    -generated
    0.07
    icontrol
    0.06
    curring
    0.06
    ंर
    0.06
     vere
    0.06
     Bible
    0.06
     frac
    0.06
    (regex
    0.06
    iciency
    0.06
    iameter
    0.06
    Act Density 0.001%

    No Known Activations