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

    Neuronpedia

    INDEX
    Explanations

    iteratively refining or adjusting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }+$
    0.49
     здесь
    0.46
    ഷി
    0.46
    ʙ
    0.46
    timevals
    0.46
    弱
    0.46
    𝚇
    0.46
    dictionary
    0.45
    iesel
    0.45
     आरबीआई
    0.45
    POSITIVE LOGITS
     in
    0.55
    ϋ
    0.54
     to
    0.51
     on
    0.50
     apro
    0.50
    Η
    0.48
     after
    0.45
     against
    0.44
     happiness
    0.44
     stal
    0.43
    Act Density 0.000%

    No Known Activations