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

    Neuronpedia

    INDEX
    Explanations

    hole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /.
    -0.07
     irreversible
    -0.06
    Turkey
    -0.06
     :-
    -0.06
     sayı
    -0.06
     baja
    -0.06
     Spanish
    -0.06
     decorator
    -0.06
     (=
    -0.06
    igham
    -0.06
    POSITIVE LOGITS
    hole
    0.24
    holes
    0.19
    -hole
    0.15
     Hole
    0.13
    ole
    0.12
    洞
    0.11
     hole
    0.11
    oles
    0.10
    OLE
    0.10
    hol
    0.09
    Act Density 0.003%

    No Known Activations