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

    Neuronpedia

    INDEX
    Explanations

    told

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    週
    -0.07
     zač
    -0.06
    uggy
    -0.06
     sailor
    -0.06
    ُر
    -0.06
    Він
    -0.06
    [strlen
    -0.06
    ındaki
    -0.06
     dabei
    -0.06
     dispositivo
    -0.06
    POSITIVE LOGITS
    ambia
    0.07
     museums
    0.07
     complement
    0.06
     WF
    0.06
    .Volume
    0.06
    대학교
    0.06
     lambda
    0.06
    EMS
    0.06
     Cov
    0.06
     oe
    0.06
    Act Density 0.013%

    No Known Activations