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

    Neuronpedia

    INDEX
    Explanations

    make or made followed by a creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     playmaker
    0.61
     dilapidated
    0.57
     लोकार्
    0.55
    aéroport
    0.55
    startGame
    0.55
    锢
    0.54
     cowardly
    0.54
     क्षतिग्रस्त
    0.54
     Bởi
    0.53
    meras
    0.52
    POSITIVE LOGITS
    q
    0.64
    كس
    0.63
    v
    0.61
    ้
    0.60
    大
    0.59
    ลา
    0.58
    3
    0.58
    、
    0.58
    u
    0.57
    (),
    0.56
    Act Density 0.062%

    No Known Activations