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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    αιδ
    -0.06
    ІІ
    -0.06
    -Free
    -0.06
     Yates
    -0.06
    士
    -0.06
     fluent
    -0.06
     bones
    -0.06
    asses
    -0.06
    .fail
    -0.06
    027
    -0.06
    POSITIVE LOGITS
    .microsoft
    0.07
    ($_
    0.07
    .contents
    0.06
     HT
    0.06
    <=$
    0.06
    VEC
    0.06
     ${↵
    0.06
     rejuven
    0.06
    ="@
    0.06
    .smart
    0.06
    Act Density 0.084%

    No Known Activations