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

    Neuronpedia

    INDEX
    Explanations

    future growth and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ů
    1.08
    с
    1.06
    ва
    1.05
    :
    0.96
    í
    0.92
    ong
    0.89
    ater
    0.89
    ur
    0.87
    ins
    0.85
    uli
    0.85
    POSITIVE LOGITS
     futura
    1.24
    ف
    1.12
    ન
    1.08
    ج
    1.02
    to
    1.01
     futuras
    1.01
    ುಂಬ
    1.00
     futuro
    0.99
    ك
    0.99
     futuros
    0.98
    Act Density 2.573%

    No Known Activations