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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wag
    -0.07
    GPS
    -0.06
     чего
    -0.06
     commenced
    -0.06
    Gear
    -0.06
     Shack
    -0.06
    �
    -0.06
    Ele
    -0.05
     quỹ
    -0.05
     Fun
    -0.05
    POSITIVE LOGITS
    aption
    0.07
    lotte
    0.07
    .Row
    0.07
    ὰ
    0.07
    طب
    0.07
     تأثیر
    0.07
     Advisor
    0.07
    (INPUT
    0.07
     salle
    0.07
     de
    0.07
    Act Density 0.065%

    No Known Activations