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

    Neuronpedia

    INDEX
    Explanations

    -d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     famed
    -0.07
    �
    -0.06
    enheim
    -0.06
     towering
    -0.06
    %H
    -0.06
     declaring
    -0.06
     typename
    -0.06
    威慑
    -0.06
     יכול
    -0.06
     chemicals
    -0.06
    POSITIVE LOGITS
    LB
    0.08
    <Edge
    0.07
    锪
    0.06
     lavor
    0.06
    .Typed
    0.06
     appointments
    0.06
     Appointment
    0.06
    Ack
    0.06
    ment
    0.06
    ผสม
    0.06
    Act Density 0.073%

    No Known Activations