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

    Neuronpedia

    INDEX
    Explanations

    Dialog snippets with parentheticals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STAT
    -0.07
    构
    -0.07
     Alo
    -0.07
    .putString
    -0.07
     Marcos
    -0.06
     patří
    -0.06
    inos
    -0.06
    aq
    -0.06
     Nose
    -0.06
     confront
    -0.06
    POSITIVE LOGITS
    атар
    0.06
    (ib
    0.06
    人民
    0.06
    ỗ
    0.06
    ButtonTitles
    0.06
     Authorities
    0.06
    .INVALID
    0.06
    (This
    0.06
    리의
    0.06
     Asi
    0.06
    Act Density 0.014%

    No Known Activations