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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nichž
    -0.08
     wie
    -0.07
    waters
    -0.06
    Wie
    -0.06
     час
    -0.06
    来た
    -0.06
    Lambda
    -0.06
    етич
    -0.06
    .fillText
    -0.06
    orsche
    -0.06
    POSITIVE LOGITS
     Goat
    0.06
    eligible
    0.06
     Admin
    0.06
     Bod
    0.06
    .secret
    0.06
     Recogn
    0.06
    -interest
    0.06
    )}↵↵
    0.06
     فرمود
    0.06
    -dismissible
    0.06
    Act Density 0.000%

    No Known Activations