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

    Neuronpedia

    INDEX
    Explanations

    Android layouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴿ
    1.65
    E
    1.54
    கடந்த
    1.50
    s
    1.41
     аз
    1.39
     whereabouts
    1.38
    न्ट
    1.38
     اُن
    1.36
    বা
    1.35
     магни
    1.32
    POSITIVE LOGITS
     trastorno
    1.65
     Hopefully
    1.61
     σχετικά
    1.59
     Compounds
    1.52
     Premises
    1.52
     tombol
    1.50
    ংলা
    1.50
     bangunan
    1.48
     neutron
    1.47
     Antibody
    1.46
    Act Density 0.006%

    No Known Activations