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

    Neuronpedia

    INDEX
    Explanations

    chain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     violently
    -0.09
    真
    -0.08
    jective
    -0.08
     goat
    -0.07
     фору
    -0.07
     aboard
    -0.07
     thesis
    -0.07
     सच
    -0.07
     sophomore
    -0.07
     Jiang
    -0.07
    POSITIVE LOGITS
     chaining
    0.16
     chained
    0.16
     successive
    0.14
     consecutive
    0.12
     consecut
    0.12
     подряд
    0.10
     chain
    0.10
     sequential
    0.10
     cascading
    0.10
    -chain
    0.10
    Act Density 0.010%

    No Known Activations