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

    Neuronpedia

    INDEX
    Explanations

    involved, in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    итом
    -0.07
     \"%
    -0.07
    QRST
    -0.07
    \"
    -0.07
    \",
    -0.07
    itr
    -0.07
    ("(
    -0.06
    *I
    -0.06
    (pipe
    -0.06
     Wonderland
    -0.06
    POSITIVE LOGITS
    xEA
    0.07
     Arrange
    0.07
     writable
    0.07
    .en
    0.06
    Kids
    0.06
    (Key
    0.06
    arming
    0.06
     indul
    0.06
    	no
    0.05
     spont
    0.05
    Act Density 0.022%

    No Known Activations