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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     করিয়াছিল
    0.34
    heiros
    0.33
     应
    0.31
     राव
    0.31
     contenant
    0.31
    这一切
    0.31
     posiada
    0.30
     करिएगा
    0.30
    केंसी
    0.30
    avacan
    0.30
    POSITIVE LOGITS
     are
    0.75
     is
    0.68
     jsou
    0.60
     आहेत
    0.58
     was
    0.54
    inafter
    0.54
     हैं
    0.53
    abouts
    0.52
    ’
    0.52
    fordshire
    0.51
    Act Density 0.026%

    No Known Activations