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

    Neuronpedia

    INDEX
    Explanations

    please provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sky
    0.47
     extraordinaire
    0.46
     THEM
    0.46
    atic
    0.46
     them
    0.46
    /
    0.45
    They
    0.45
     us
    0.45
    Oh
    0.44
    ITS
    0.43
    POSITIVE LOGITS
     Proceed
    0.76
    <unused2148>
    0.74
     revising
    0.73
    苧
    0.72
    <unused749>
    0.72
     proceeding
    0.71
     гуляць
    0.68
     meminta
    0.68
     rostrum
    0.68
     رؤ
    0.67
    Act Density 0.772%

    No Known Activations