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

    Neuronpedia

    INDEX
    Explanations

    there are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இவற்றை
    0.84
    ങ്ങളാണ്
    0.79
    助于
    0.73
    개를
    0.72
    வற்றை
    0.71
    かを
    0.67
    もので
    0.65
    만을
    0.64
     பெற்றது
    0.64
     hvilket
    0.64
    POSITIVE LOGITS
     there
    6.91
    there
    6.17
    There
    5.56
     There
    5.54
     THERE
    5.12
     هناك
    5.06
    THERE
    4.52
     theres
    4.38
     там
    3.84
     देयर
    3.78
    Act Density 1.294%

    No Known Activations