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

    Neuronpedia

    INDEX
    Explanations

    appearance and minimize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.55
    са
    0.53
    то
    0.52
    стри
    0.50
    ра
    0.49
    рда
    0.49
    تا
    0.47
     thanking
    0.47
    та
    0.46
    سا
    0.46
    POSITIVE LOGITS
     نتیجہ
    0.48
    abi
    0.45
    ämp
    0.44
     품질
    0.44
    iner
    0.43
     ለመ
    0.43
    oh
    0.43
     መ
    0.43
    amentos
    0.43
    ager
    0.42
    Act Density 0.063%

    No Known Activations