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

    Neuronpedia

    INDEX
    Explanations

    Abstracts and summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dzięki
    -0.07
    ൾ
    -0.07
     validated
    -0.07
     конкр
    -0.07
     Cancel
    -0.07
    浦东
    -0.07
     контр
    -0.07
     �
    -0.07
     MatTable
    -0.07
    ﱃ
    -0.06
    POSITIVE LOGITS
    “There
    0.07
    Suite
    0.07
    .LayoutStyle
    0.07
    There
    0.07
    EQ
    0.07
     earrings
    0.07
    iko
    0.07
    Ｑ
    0.07
    传输
    0.06
    Pros
    0.06
    Act Density 0.007%

    No Known Activations