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

    Neuronpedia

    INDEX
    Explanations

    attach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keyword
    -0.07
     timestamp
    -0.07
     SAMPLE
    -0.06
     Moore
    -0.06
     MOD
    -0.06
    markdown
    -0.06
     pipeline
    -0.06
     debtor
    -0.06
    융
    -0.06
    Timestamp
    -0.06
    POSITIVE LOGITS
    }s
    0.07
    těž
    0.07
     Katy
    0.06
     Cougar
    0.06
     gathers
    0.06
     Bengals
    0.06
     Photographer
    0.06
     přib
    0.06
     Gather
    0.06
     Hij
    0.06
    Act Density 0.002%

    No Known Activations