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

    Neuronpedia

    INDEX
    Explanations

    strong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lug
    -0.07
    _tim
    -0.07
    izz
    -0.07
    arith
    -0.06
    .echo
    -0.06
    _threads
    -0.06
    xff
    -0.06
    .visit
    -0.06
    get
    -0.06
     akıl
    -0.06
    POSITIVE LOGITS
     Expo
    0.07
    kinci
    0.07
    ,strong
    0.06
     Refriger
    0.06
     manned
    0.06
     vbox
    0.06
    queueReusable
    0.06
    Outlined
    0.06
     unmanned
    0.06
    окол
    0.06
    Act Density 0.001%

    No Known Activations