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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ing
    -0.07
    της
    -0.07
     Flag
    -0.07
    汇
    -0.06
    ίζει
    -0.06
    using
    -0.06
    因
    -0.06
    ||||
    -0.06
    field
    -0.06
     نفسه
    -0.06
    POSITIVE LOGITS
     afterEach
    0.06
     subscription
    0.06
    .vec
    0.06
     znal
    0.06
     Bren
    0.06
     Dodd
    0.06
     expected
    0.06
    trace
    0.06
     Karn
    0.06
     xc
    0.06
    Act Density 0.033%

    No Known Activations