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

    Neuronpedia

    INDEX
    Explanations

    Code properties and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NavLink
    -0.07
    983
    -0.06
    elon
    -0.06
    Chair
    -0.06
    /fire
    -0.06
    ลง
    -0.06
     وفق
    -0.06
     رب
    -0.06
    _topics
    -0.05
    bak
    -0.05
    POSITIVE LOGITS
     tetas
    0.07
     butcher
    0.07
    .classList
    0.06
    ництво
    0.06
    (py
    0.06
    .actions
    0.06
     afforded
    0.06
     Gerard
    0.06
     perpetrated
    0.06
    Canceled
    0.06
    Act Density 0.016%

    No Known Activations