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

    Neuronpedia

    INDEX
    Explanations

    units and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posing
    0.75
     AttributeError
    0.74
     stemming
    0.72
     Spec
    0.71
     refresh
    0.68
     love
    0.68
     integrity
    0.68
    ிரா
    0.67
     ham
    0.67
    tains
    0.66
    POSITIVE LOGITS
     वीं
    1.30
    ویں
    1.23
     pulgadas
    1.23
    वीं
    1.22
    वें
    1.20
    th
    1.18
     మంది
    1.16
     minutos
    1.15
    ″
    1.06
     pouces
    1.05
    Act Density 0.595%

    No Known Activations