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

    Neuronpedia

    INDEX
    Explanations

    causes a result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旂
    0.43
     बताना
    0.43
    roga
    0.43
    懾
    0.42
     asegurarse
    0.41
    லைப்
    0.40
    是将
    0.40
    ຮັບ
    0.40
     помога
    0.39
     estaven
    0.39
    POSITIVE LOGITS
    导致
    1.95
    導致
    1.86
     منجر
    1.80
     resulting
    1.67
     resulted
    1.67
     causing
    1.60
     menyebabkan
    1.52
     leads
    1.45
    resulting
    1.42
     باعث
    1.38
    Act Density 0.045%

    No Known Activations