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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🙌
    -0.08
     startTime
    -0.08
    .startTime
    -0.08
    starttime
    -0.07
     WaitForSeconds
    -0.07
     lå
    -0.07
     drużyn
    -0.07
    负面
    -0.07
     شكرا
    -0.07
     kullan
    -0.07
    POSITIVE LOGITS
    Torrent
    0.07
    洲
    0.07
    잪
    0.07
    ери
    0.07
    acher
    0.07
    فقد
    0.07
    	mock
    0.07
    咤
    0.07
    WORK
    0.07
    เขต
    0.06
    Act Density 0.038%

    No Known Activations