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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pedestal
    -0.07
    Ye
    -0.07
    ADR
    -0.06
    Symbols
    -0.05
     Db
    -0.05
    Tre
    -0.05
    {/
    -0.05
     Crafts
    -0.05
     freezer
    -0.05
    Mc
    -0.05
    POSITIVE LOGITS
     Olivier
    0.12
    -upload
    0.08
    -out
    0.07
    平均
    0.07
     мил
    0.06
     aired
    0.06
    .over
    0.06
     streams
    0.06
     yahoo
    0.06
     ↵	↵
    0.06
    Act Density 0.002%

    No Known Activations