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

    Neuronpedia

    INDEX
    Explanations

    easy to understand or implement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Z
    0.82
    सी
    0.78
    М
    0.77
    Մ
    0.77
    '
    0.76
    ির
    0.74
    Μ
    0.73
    Ι
    0.73
    U
    0.71
    ’
    0.70
    POSITIVE LOGITS
    -
    0.84
    易
    0.71
     dàng
    0.69
     fácil
    0.69
     hitta
    0.63
     fáciles
    0.62
     breezy
    0.62
    롭게
    0.61
    hopping
    0.59
     revolt
    0.58
    Act Density 0.098%

    No Known Activations