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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with "calculate"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    也許
    0.44
    "?
    0.44
    かもしれませんが
    0.44
    fors
    0.43
     buildFor
    0.43
    不喜欢
    0.43
     proposent
    0.42
    ដឹក
    0.42
    ាប់
    0.41
     सॉरी
    0.41
    POSITIVE LOGITS
    9
    0.49
    angga
    0.46
    واز
    0.44
     మంది
    0.43
     sucesso
    0.42
    oción
    0.42
    izamos
    0.40
     organismo
    0.40
    anggung
    0.40
     decena
    0.40
    Act Density 0.003%

    No Known Activations