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

    Neuronpedia

    INDEX
    Explanations

    a phrase indicating the speaker is checking for errors

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eries
    -0.08
    ands
    -0.07
    incinn
    -0.06
    LineColor
    -0.06
     Brut
    -0.06
    TECTED
    -0.06
     Landing
    -0.06
    ValuePair
    -0.06
    IntArray
    -0.06
     landing
    -0.06
    POSITIVE LOGITS
     especially
    0.07
    onis
    0.07
    arih
    0.06
    abb
    0.06
    ABB
    0.06
    egade
    0.06
     especialmente
    0.06
     particularly
    0.06
    especially
    0.06
    hidden
    0.06
    Act Density 0.061%

    No Known Activations