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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slain
    -0.07
     thịt
    -0.06
    ůst
    -0.06
    楼
    -0.06
    Important
    -0.06
    �
    -0.06
    αλύτε
    -0.06
     вла
    -0.06
    ंपर
    -0.06
    اسطة
    -0.06
    POSITIVE LOGITS
     peculiar
    0.07
     administered
    0.07
     Each
    0.06
     k
    0.06
     target
    0.06
     　 　 　 　 　 　 　 　
    0.06
    ,LOCATION
    0.06
     considering
    0.06
    raits
    0.06
    ,value
    0.06
    Act Density 0.252%

    No Known Activations