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

    Neuronpedia

    INDEX
    Explanations

    business owner letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    心地
    0.40
    盡
    0.37
    rati
    0.36
    儘
    0.36
    :].
    0.36
     жүктөп
    0.35
     ఏర్ప
    0.35
     GetData
    0.35
    =")
    0.35
     இருந்த
    0.34
    POSITIVE LOGITS
    BIN
    0.42
     nodo
    0.40
     Crescent
    0.40
     LIB
    0.39
    袂
    0.38
     ऑस्ट्रेलिया
    0.38
     Italiano
    0.38
    AMPLE
    0.38
     таким
    0.37
    Assume
    0.37
    Act Density 0.003%

    No Known Activations