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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -highlight
    -0.07
     bekl
    -0.06
    roots
    -0.06
    ие
    -0.06
    -table
    -0.06
    okay
    -0.06
    zf
    -0.06
     }
↵
    -0.06
     whenever
    -0.06
    -chain
    -0.06
    POSITIVE LOGITS
    .authorization
    0.07
    .intellij
    0.07
     zaj
    0.06
     yaml
    0.06
     표
    0.06
     보호
    0.06
     پای
    0.06
     interle
    0.06
     eigen
    0.06
    bst
    0.06
    Act Density 0.828%

    No Known Activations