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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Futures
    -0.07
    severity
    -0.07
    реж
    -0.06
    Indiana
    -0.06
    ↵↵    ↵
    -0.06
    _queries
    -0.06
    수의
    -0.06
    Spoiler
    -0.06
    Saga
    -0.06
     Domestic
    -0.06
    POSITIVE LOGITS
     DESCRIPTION
    0.07
     retrieves
    0.06
     curiosity
    0.06
     SHORT
    0.06
    .preventDefault
    0.06
    ，不
    0.06
     Garr
    0.06
    िब
    0.06
    osing
    0.06
     hoặc
    0.06
    Act Density 0.000%

    No Known Activations