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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isto
    -0.08
     Brooke
    -0.08
    ko
    -0.08
    撰写
    -0.07
     Mentor
    -0.07
    sto
    -0.07
    .addTo
    -0.07
    gett
    -0.07
     Bit
    -0.07
     pitching
    -0.07
    POSITIVE LOGITS
     functionName
    0.07
    עולם
    0.06
    Banner
    0.06
     punctuation
    0.06
     //}↵
    0.06
     Ergebn
    0.06
    ookeeper
    0.06
     Summer
    0.06
    ='')↵
    0.06
     multiples
    0.06
    Act Density 0.003%

    No Known Activations