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

    Neuronpedia

    INDEX
    Explanations

    IELTS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ần
    -0.06
     crusher
    -0.06
    !)↵
    -0.06
    VarChar
    -0.06
     physicists
    -0.06
     Selling
    -0.06
    ��
    -0.06
    Du
    -0.06
    -eye
    -0.06
    -pane
    -0.06
    POSITIVE LOGITS
     فهرست
    0.07
     повинен
    0.06
    三三
    0.06
    还是
    0.06
     접
    0.06
     ΠΡ
    0.06
    SF
    0.06
    basic
    0.06
    卓
    0.06
    都是
    0.06
    Act Density 0.011%

    No Known Activations