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

    Neuronpedia

    INDEX
    Explanations

    The Wizard of Oz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㑔
    0.47
     определения
    0.46
    撗
    0.45
     способны
    0.45
     поддерживает
    0.45
     સંદ
    0.44
    宄
    0.44
     бош
    0.44
     परिश
    0.44
    FocusValue
    0.44
    POSITIVE LOGITS
     theses
    0.44
     bungalows
    0.43
     mysterious
    0.43
     goût
    0.43
     involving
    0.42
     oiseaux
    0.41
     medicine
    0.41
     things
    0.41
     tasted
    0.41
     breakfast
    0.40
    Act Density 0.001%

    No Known Activations