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

    Neuronpedia

    INDEX
    Explanations

    Simultaneously

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chr
    -0.07
    chrift
    -0.07
    mtree
    -0.07
     overrides
    -0.07
     columnIndex
    -0.07
     Outputs
    -0.06
    说道
    -0.06
    utils
    -0.06
    etable
    -0.06
    brands
    -0.06
    POSITIVE LOGITS
    ramid
    0.07
    Separ
    0.07
    smith
    0.06
    025
    0.06
    ‌کرد
    0.06
    任务
    0.06
     sharply
    0.06
     it
    0.06
     fichier
    0.06
    )]↵↵
    0.06
    Act Density 0.008%

    No Known Activations