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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    joining
    -0.08
     تاز
    -0.08
    طرح
    -0.07
     Joining
    -0.07
     (>
    -0.07
     rocking
    -0.07
     temperatur
    -0.07
     joining
    -0.07
     ince
    -0.07
    herence
    -0.07
    POSITIVE LOGITS
     abbrevi
    0.18
     abbreviation
    0.18
     abbreviated
    0.17
     shorthand
    0.16
     shortened
    0.15
     shorten
    0.13
     сокращ
    0.13
    缩
    0.13
     shortening
    0.13
     concise
    0.12
    Act Density 0.023%

    No Known Activations