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

    Neuronpedia

    INDEX
    Explanations

    primarily acquires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Assume
    0.40
     dt
    0.39
    Assume
    0.39
     +
    0.39
    elez
    0.39
     souligne
    0.38
    multi
    0.38
     мат
    0.38
     assumes
    0.37
     formulation
    0.37
    POSITIVE LOGITS
     grandsons
    0.43
     хра
    0.42
    ◘
    0.41
     conoscenza
    0.40
     ಕುಟುಂಬ
    0.40
    氅
    0.39
     widowed
    0.38
     prostitute
    0.38
     grandchild
    0.38
    oculars
    0.37
    Act Density 0.001%

    No Known Activations