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

    Neuronpedia

    INDEX
    Explanations

    catch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    508
    -0.07
     simulations
    -0.07
     multiples
    -0.07
     simulation
    -0.07
     Maple
    -0.06
    (poly
    -0.06
     multimedia
    -0.06
     Disk
    -0.06
    ウェ
    -0.06
    Revision
    -0.06
    POSITIVE LOGITS
     catch
    0.10
     Caught
    0.09
    catch
    0.09
     catching
    0.09
    -catching
    0.08
    ATCH
    0.08
    �
    0.08
     Catch
    0.07
    atch
    0.07
     catcher
    0.07
    Act Density 0.011%

    No Known Activations