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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ez
    -0.07
    ायत
    -0.07
     بیر
    -0.06
     aio
    -0.06
    �
    -0.06
     Sponge
    -0.06
     Firewall
    -0.06
    -part
    -0.06
     东
    -0.06
    oir
    -0.06
    POSITIVE LOGITS
    πουλος
    0.07
     �
    0.06
    Dragging
    0.06
    .getBytes
    0.06
    odesk
    0.06
     Örneğin
    0.06
    Exclude
    0.06
     包
    0.06
    朋
    0.06
     excav
    0.06
    Act Density 0.017%

    No Known Activations