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
     Ξ
    -0.06
    .readAs
    -0.06
    én
    -0.06
    ụ
    -0.06
    郡
    -0.06
     terrorism
    -0.06
    _OC
    -0.06
    ίου
    -0.06
    862
    -0.06
     getaway
    -0.06
    POSITIVE LOGITS
     atte
    0.07
     між
    0.07
    (Math
    0.07
    (jq
    0.06
     ung
    0.06
    ,h
    0.06
     Validate
    0.06
    .platform
    0.06
     выпол
    0.06
    ATS
    0.06
    Act Density 0.042%

    No Known Activations