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

    Neuronpedia

    INDEX
    Explanations

    3D followed by objects/concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kub
    0.36
    N
    0.36
    0.36
    Hull
    0.35
     sized
    0.35
     larg
    0.35
    A
    0.34
    更
    0.34
    est
    0.34
    Est
    0.34
    POSITIVE LOGITS
    ըն
    0.45
    ihanna
    0.41
    捪
    0.39
    বিজ্ঞ
    0.37
    㚐
    0.37
     SPACE
    0.37
    स्थल
    0.37
     პროფილი
    0.36
     Ising
    0.36
     proyección
    0.36
    Act Density 0.011%

    No Known Activations