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

    Neuronpedia

    INDEX
    Explanations

    street names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Group
    -0.07
     Grat
    -0.06
    젝
    -0.06
    .shell
    -0.06
    ็นอ
    -0.06
     slogan
    -0.06
    jím
    -0.06
    .cond
    -0.06
    (bc
    -0.06
     省
    -0.06
    POSITIVE LOGITS
    ende
    0.07
     STREET
    0.07
     instructors
    0.07
    ICODE
    0.06
    Operating
    0.06
     Street
    0.06
    مد
    0.06
     warning
    0.06
    怀
    0.06
     presenting
    0.06
    Act Density 0.014%

    No Known Activations