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

    Neuronpedia

    INDEX
    Explanations

    approximations and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aq
    0.51
    f
    0.51
    ant
    0.50
     potens
    0.47
    d
    0.47
    ()
    0.46
    ح
    0.46
    defined
    0.46
    tem
    0.46
    antas
    0.44
    POSITIVE LOGITS
     ServicePolicy
    0.50
    Hozzáférés
    0.47
    လည်း
    0.45
     Emerging
    0.43
    LARGE
    0.43
     Tory
    0.42
    linkOpacity
    0.42
     nCenters
    0.42
    iť
    0.41
     Pairing
    0.41
    Act Density 0.001%

    No Known Activations