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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .prepend
    -0.07
     preset
    -0.07
     sand
    -0.07
    ai
    -0.07
    ลอง
    -0.07
     strong
    -0.07
    xdd
    -0.07
    draw
    -0.07
     free
    -0.07
    rai
    -0.07
    POSITIVE LOGITS
     giọng
    0.07
    𬱟
    0.07
    azers
    0.07
    }}">{{$
    0.07
     locales
    0.07
    攻关
    0.06
    ⿊
    0.06
     }));↵↵
    0.06
    بحث
    0.06
    authors
    0.06
    Act Density 0.027%

    No Known Activations