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
     Pero
    -0.07
     Petro
    -0.07
    .lucene
    -0.07
     Oro
    -0.07
     Studies
    -0.07
     버
    -0.07
     erupt
    -0.07
    Studies
    -0.07
     surpr
    -0.06
     Pap
    -0.06
    POSITIVE LOGITS
     chain
    0.16
     Chain
    0.15
     chains
    0.14
    chain
    0.12
    Chain
    0.12
    -chain
    0.11
     Chains
    0.11
    .chain
    0.10
     chained
    0.09
    _chain
    0.09
    Act Density 0.012%

    No Known Activations