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

    Neuronpedia

    INDEX
    Explanations

    actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आणि
    0.49
    受信
    0.46
    并在
    0.45
     और
    0.45
     దక్షిణ
    0.45
    公开
    0.44
    ર્ટ
    0.44
    规范
    0.44
    வதற்காக
    0.44
    科技有限公司
    0.44
    POSITIVE LOGITS
     entweder
    0.45
     neoplasms
    0.44
    rightarrow
    0.41
     solutions
    0.41
    $\
    0.40
     maladies
    0.40
     nemmeno
    0.40
     luck
    0.40
     przypad
    0.40
     waarbij
    0.40
    Act Density 0.001%

    No Known Activations