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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <l
    -0.07
    Floor
    -0.07
     Submission
    -0.07
    (stock
    -0.07
    -rock
    -0.06
     annotation
    -0.06
    .proxy
    -0.06
    Labels
    -0.06
    Rule
    -0.06
    ublisher
    -0.06
    POSITIVE LOGITS
     dearly
    0.06
     大阪
    0.06
     IPA
    0.06
    ,:]
    0.06
     večer
    0.06
    threat
    0.06
     Gaza
    0.06
     Illustrated
    0.06
     soir
    0.06
    xEF
    0.06
    Act Density 0.003%

    No Known Activations