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

    Neuronpedia

    INDEX
    Explanations

    butter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blockchain
    -0.07
     잠
    -0.07
     toddlers
    -0.06
     encoding
    -0.06
    ock
    -0.06
    .Mar
    -0.06
     hisset
    -0.06
    irez
    -0.06
     wilderness
    -0.06
     Sons
    -0.06
    POSITIVE LOGITS
    estruct
    0.07
     migli
    0.07
     informações
    0.06
     doc
    0.06
     qq
    0.06
    GUI
    0.06
     butter
    0.06
     glyc
    0.06
    -office
    0.06
    -nine
    0.06
    Act Density 0.002%

    No Known Activations