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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =$(
    -0.09
     Ganze
    -0.08
     eterna
    -0.08
     devoir
    -0.08
     besondere
    -0.07
    cos
    -0.07
    Special
    -0.07
     пришлось
    -0.07
    어
    -0.07
     eterno
    -0.07
    POSITIVE LOGITS
     кроме
    0.15
     whatsoever
    0.14
     behalve
    0.14
     imaginable
    0.13
     excepto
    0.12
    都
    0.11
     except
    0.11
    except
    0.11
     Except
    0.10
     будь
    0.10
    Act Density 0.176%

    No Known Activations