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

    Neuronpedia

    INDEX
    Explanations

    objects and their elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wifery
    0.72
    initState
    0.69
    ünschen
    0.69
     réservation
    0.66
     philosophie
    0.64
    spirited
    0.63
    missione
    0.63
     менедж
    0.63
    дро
    0.63
    mère
    0.63
    POSITIVE LOGITS
     objects
    2.37
    objects
    1.94
     objetos
    1.94
     Objects
    1.90
     shapes
    1.75
     object
    1.74
     objets
    1.74
    Objects
    1.71
     oggetti
    1.71
     textures
    1.65
    Act Density 0.402%

    No Known Activations