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

    Neuronpedia

    INDEX
    Explanations

    code snippets and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TCP
    -0.07
     ном
    -0.07
    Comments
    -0.06
     потер
    -0.06
     evaluation
    -0.06
     radi
    -0.06
     Liu
    -0.06
     richest
    -0.06
    Ed
    -0.06
     investigation
    -0.06
    POSITIVE LOGITS
    (UnmanagedType
    0.07
    .clicked
    0.06
    >')↵
    0.06
    ulsion
    0.06
    faf
    0.06
    lexport
    0.06
         
↵
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
    formace
    0.06
    .Dense
    0.06
    Act Density 0.012%

    No Known Activations