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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chẳng
    0.93
    '
    0.86
    sun
    0.85
     delir
    0.84
    sda
    0.82
     grub
    0.82
    0.82
     rosette
    0.81
    sat
    0.80
    m
    0.80
    POSITIVE LOGITS
    во
    1.03
    ट्टर
    1.00
    Ⴀ
    0.97
    ます
    0.93
    з
    0.92
    IsValid
    0.91
    Determine
    0.90
    Tienes
    0.89
    ᆼ
    0.88
    ría
    0.88
    Act Density 0.142%

    No Known Activations