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

    Neuronpedia

    INDEX
    Explanations

    breeding and reproduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prank
    0.58
     dads
    0.58
     smelly
    0.55
    для
    0.55
     кора
    0.54
    اهده
    0.54
    <unused32>
    0.54
    यंस
    0.53
    野球
    0.53
    millimeters
    0.53
    POSITIVE LOGITS
     Margaret
    0.49
    Margaret
    0.46
     सप्त
    0.45
    North
    0.42
     போது
    0.40
     poświę
    0.40
    Kate
    0.40
     संकल्प
    0.39
    Jones
    0.39
    ற்
    0.38
    Act Density 0.002%

    No Known Activations