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

    Neuronpedia

    INDEX
    Explanations

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    THR
    -0.07
    conomy
    -0.07
     Graphic
    -0.06
    ergency
    -0.06
     automated
    -0.06
    чил
    -0.06
     Swan
    -0.06
    âm
    -0.06
     Adapt
    -0.06
    داری
    -0.06
    POSITIVE LOGITS
    (objects
    0.07
    )},↵
    0.07
    채
    0.07
    心里
    0.06
    ë
    0.06
     Jes
    0.06
    減
    0.06
     دقیق
    0.06
    ni
    0.06
     lesbian
    0.06
    Act Density 0.003%

    No Known Activations