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

    Neuronpedia

    INDEX
    Explanations

    online shopping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tower
    -0.07
     git
    -0.07
    __':↵
    -0.07
    Git
    -0.07
     labour
    -0.07
     eg
    -0.07
     ellen
    -0.07
    ',...↵
    -0.07
    Ã
    -0.07
     informer
    -0.07
    POSITIVE LOGITS
    skip
    0.09
     voie
    0.08
     Sharks
    0.08
     sèl
    0.08
    _skip
    0.08
     uninterrupted
    0.08
     selenium
    0.08
    .skip
    0.08
    Skip
    0.08
     Peng
    0.08
    Act Density 0.003%

    No Known Activations