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

    Neuronpedia

    INDEX
    Explanations

    768

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -disc
    -0.07
    -free
    -0.07
    342
    -0.07
    044
    -0.07
    _state
    -0.06
    282
    -0.06
    �
    -0.06
    (cancel
    -0.06
    435
    -0.06
    -required
    -0.06
    POSITIVE LOGITS
    768
    0.35
    769
    0.11
    767
    0.11
     šp
    0.06
    iefs
    0.06
     overwhelmingly
    0.06
     mev
    0.06
     감
    0.06
    hamster
    0.06
    шт
    0.06
    Act Density 0.001%

    No Known Activations