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

    Neuronpedia

    INDEX
    Explanations

    concise writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     short
    1.59
     корот
    1.47
     짧
    1.45
    short
    1.44
    短
    1.37
    短い
    1.36
    Short
    1.30
    짧
    1.30
     SHORT
    1.30
     Short
    1.29
    POSITIVE LOGITS
    Conc
    1.57
     conc
    1.54
     Conc
    1.48
    conc
    1.42
     Concise
    1.40
     concise
    1.30
     concave
    1.02
     concisely
    1.02
     konc
    0.97
     concierge
    0.92
    Act Density 0.119%

    No Known Activations