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

    Neuronpedia

    INDEX
    Explanations

    keycloak, numbers, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Plenum
    0.57
     Viele
    0.55
    Historia
    0.54
    TV
    0.54
     ಅಥವಾ
    0.52
     Panorama
    0.52
     Botanic
    0.52
     Outdoor
    0.52
     અથવા
    0.51
     Ethn
    0.51
    POSITIVE LOGITS
     médicament
    0.66
     dois
    0.65
     précision
    0.64
     numeracy
    0.63
     prestazioni
    0.61
     blanchâtre
    0.59
     três
    0.59
     calculadora
    0.59
     geometría
    0.58
     doppia
    0.58
    Act Density 0.038%

    No Known Activations