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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     META
    -0.08
    tingham
    -0.07
    Tag
    -0.07
     LG
    -0.06
    반기
    -0.06
     багато
    -0.06
    flation
    -0.06
    Categories
    -0.06
    LG
    -0.06
     plethora
    -0.06
    POSITIVE LOGITS
    ibt
    0.07
     आस
    0.07
     unreachable
    0.07
     kost
    0.06
    -fields
    0.06
    ci
    0.06
     Score
    0.06
     ذکر
    0.06
    ाम
    0.06
    ?>><?
    0.06
    Act Density 0.008%

    No Known Activations