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

    Neuronpedia

    INDEX
    Explanations

    fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ultipl
    0.65
     dày
    0.62
    垕
    0.62
     భారీ
    0.61
    Caro
    0.61
    uyente
    0.60
     ભારે
    0.60
     entorno
    0.59
    㡷
    0.59
    ಬೇ
    0.58
    POSITIVE LOGITS
     tiny
    1.60
     flicker
    1.57
     glimpse
    1.53
     speck
    1.53
     snippet
    1.52
     glimpses
    1.50
     flashes
    1.49
     fragment
    1.48
     fragments
    1.47
     hint
    1.44
    Act Density 0.821%

    No Known Activations