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

    Neuronpedia

    INDEX
    Explanations

    questioning or doubt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BAL
    -0.09
    Бал
    -0.09
     balancing
    -0.08
    BAL
    -0.08
    (ptr
    -0.08
    Bal
    -0.08
     équilibr
    -0.08
    σο
    -0.07
    Accel
    -0.07
     initiatives
    -0.07
    POSITIVE LOGITS
     unequiv
    0.15
     unmistak
    0.12
     certainty
    0.11
    明确
    0.11
     conclus
    0.11
    нознач
    0.10
     confirmé
    0.10
     incontro
    0.10
     confirmed
    0.10
     évidence
    0.10
    Act Density 0.104%

    No Known Activations