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

    Neuronpedia

    INDEX
    Explanations

    parameters and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంచ్
    0.38
     getState
    0.37
     Yaad
    0.36
     Subtract
    0.36
     تنت
    0.36
     Quickly
    0.36
    ದು
    0.36
     dragState
    0.35
    ᴜ
    0.35
    ừa
    0.35
    POSITIVE LOGITS
    BTC
    0.40
     moral
    0.39
     delf
    0.37
     administered
    0.37
    administered
    0.37
    स्तानी
    0.36
     بدی
    0.35
     дело
    0.35
    centred
    0.35
     democratic
    0.34
    Act Density 0.001%

    No Known Activations