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

    Neuronpedia

    INDEX
    Explanations

    ball into position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ત્મ
    0.71
     sprinting
    0.69
    Sprint
    0.69
     Sprint
    0.67
     sprint
    0.67
    তাদের
    0.65
    इकिल
    0.65
     bewegen
    0.63
     يستخدم
    0.63
    Initialized
    0.63
    POSITIVE LOGITS
     into
    1.09
     towards
    0.93
    into
    0.86
     toward
    0.84
     Into
    0.77
     onto
    0.75
     vào
    0.75
     down
    0.75
     Towards
    0.75
     naar
    0.74
    Act Density 0.006%

    No Known Activations