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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แรก
    -0.06
    ule
    -0.06
    ulary
    -0.06
     consciousness
    -0.06
     Wellness
    -0.06
    [now
    -0.06
    AAAAAAAA
    -0.06
    들도
    -0.06
    ्वर
    -0.06
    ською
    -0.06
    POSITIVE LOGITS
     itir
    0.07
     reinstall
    0.07
    avic
    0.07
    string
    0.06
    sip
    0.06
    Ин
    0.06
    лия
    0.06
     sister
    0.06
     Books
    0.06
     bàn
    0.06
    Act Density 0.033%

    No Known Activations