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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сов
    -0.07
     Supporters
    -0.07
     asp
    -0.07
     �
    -0.06
    	items
    -0.06
    Fizz
    -0.06
     respects
    -0.06
     Ethiopia
    -0.06
     onResume
    -0.06
     전문
    -0.06
    POSITIVE LOGITS
    da
    0.07
    Ga
    0.07
    ilia
    0.07
    stru
    0.07
    ˘
    0.07
     clo
    0.07
    ीए
    0.06
    letion
    0.06
                            ↵
    0.06
     黄
    0.06
    Act Density 0.000%

    No Known Activations