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

    Neuronpedia

    INDEX
    Explanations

    derived from sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ['*.
    0.38
     стоимо
    0.38
     blobs
    0.37
    AddField
    0.37
     powst
    0.36
     конкурен
    0.36
     prej
    0.36
     situational
    0.36
     ugljik
    0.36
     রশ্ম
    0.36
    POSITIVE LOGITS
     borrowed
    1.84
     adapted
    1.70
    Adapted
    1.69
     Adapted
    1.63
    adapted
    1.55
    Borrowed
    1.50
     derived
    1.48
    borrow
    1.41
     borrow
    1.32
     borrowing
    1.32
    Act Density 0.038%

    No Known Activations