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

    Neuronpedia

    INDEX
    Explanations

    know about or know how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FBSDKAccessToken
    0.41
    บน
    0.39
    ادار
    0.37
    anker
    0.36
    centerY
    0.35
    你的
    0.35
    小的
    0.35
    efined
    0.35
    णे
    0.35
    आई
    0.34
    POSITIVE LOGITS
    t
    0.55
     orchid
    0.47
    w
    0.46
    m
    0.45
    ש
    0.44
     days
    0.44
     had
    0.43
    é
    0.42
     incest
    0.40
     this
    0.40
    Act Density 0.249%

    No Known Activations