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

    Neuronpedia

    INDEX
    Explanations

    Chess board orientation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .keyword
    -0.08
     inte
    -0.08
    ____
    -0.07
     deductible
    -0.07
     mä
    -0.07
     kicked
    -0.07
    ांस
    -0.07
    _keyword
    -0.07
     whitelist
    -0.07
     damp
    -0.07
    POSITIVE LOGITS
     Leonardo
    0.10
     convention
    0.09
     conventions
    0.09
     принято
    0.09
     Starbucks
    0.09
     iconic
    0.09
     abak
    0.08
     Memor
    0.08
     zasad
    0.08
     γε
    0.08
    Act Density 0.014%

    No Known Activations