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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Regarding
    -0.07
    א
    -0.06
     объект
    -0.06
    ()])↵
    -0.06
     Mär
    -0.06
     daddy
    -0.06
     Gat
    -0.06
     sg
    -0.06
     sunday
    -0.06
     M
    -0.06
    POSITIVE LOGITS
    chrom
    0.07
    ليف
    0.07
    ustralia
    0.07
    оф
    0.06
    jf
    0.06
    ICENSE
    0.06
     polis
    0.06
     Accessories
    0.06
     अफ
    0.06
    _connector
    0.06
    Act Density 0.318%

    No Known Activations