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

    Neuronpedia

    INDEX
    Explanations

    something has just begun

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prin
    -0.07
     Therapy
    -0.06
     영국
    -0.06
    Fan
    -0.06
     Stefan
    -0.06
     Gro
    -0.06
    riv
    -0.06
     متف
    -0.06
     mock
    -0.06
    /an
    -0.06
    POSITIVE LOGITS
    skými
    0.07
    SSID
    0.07
    ("("
    0.06
    ben
    0.06
     广
    0.06
    );}↵
    0.06
    κά
    0.06
    .CommandText
    0.06
    Ž
    0.06
     illumin
    0.06
    Act Density 0.053%

    No Known Activations