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

    Neuronpedia

    INDEX
    Explanations

    standard deviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fda
    0.50
    ändert
    0.47
    ವಿಲ್ಲ
    0.47
    <unused333>
    0.46
    ❚
    0.46
     jangka
    0.46
    èlement
    0.45
    elang
    0.45
     ballad
    0.44
     üretim
    0.44
    POSITIVE LOGITS
    ෞ
    0.45
    ্রম
    0.44
     |=
    0.43
     perro
    0.42
     Lord
    0.41
    إ
    0.41
    ᴘ
    0.40
    マ
    0.40
     ऑफ़
    0.39
    貉
    0.39
    Act Density 0.000%

    No Known Activations