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

    Neuronpedia

    INDEX
    Explanations

    manual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GREEN
    -0.08
    烔
    -0.07
    Ground
    -0.07
     Eigen
    -0.07
    網友
    -0.07
     rospy
    -0.06
    JsonObject
    -0.06
     nâ
    -0.06
    romosome
    -0.06
     grip
    -0.06
    POSITIVE LOGITS
    appointment
    0.07
    🐼
    0.07
    asing
    0.07
    شركات
    0.07
    OAuth
    0.07
    Ⱑ
    0.07
    .telegram
    0.07
    php
    0.06
     Alerts
    0.06
    quent
    0.06
    Act Density 0.005%

    No Known Activations