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

    Neuronpedia

    INDEX
    Explanations

    catching exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thickness
    0.38
    ෑ
    0.38
    ྒ
    0.38
    Thought
    0.37
     thinks
    0.35
     flange
    0.35
    と思って
    0.35
     düşün
    0.34
    äus
    0.34
    вих
    0.34
    POSITIVE LOGITS
     catch
    1.51
    catch
    1.41
     Catch
    1.33
     catching
    1.30
    Catch
    1.27
     catches
    1.20
    catching
    1.04
     caught
    0.91
    except
    0.90
     except
    0.88
    Act Density 0.017%

    No Known Activations