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

    Neuronpedia

    INDEX
    Explanations

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এদিকে
    0.77
     salient
    0.71
     flexibly
    0.68
     assertive
    0.68
     hereby
    0.68
     signatory
    0.64
     tasty
    0.63
     sectors
    0.62
     simultaneously
    0.62
     localised
    0.61
    POSITIVE LOGITS
    ，“
    1.27
    ，「
    1.08
    ‶
    1.08
     "'
    1.07
     “
    1.06
     „
    1.05
     “‘
    1.03
    .“
    1.00
     "
    0.99
     “,
    0.98
    Act Density 0.003%

    No Known Activations