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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ray
    -0.07
     dob
    -0.07
    Virtual
    -0.07
    toggleClass
    -0.06
    _exam
    -0.06
     comforting
    -0.06
    /New
    -0.06
     이를
    -0.06
     ویرایش
    -0.06
    -medium
    -0.06
    POSITIVE LOGITS
     Mining
    0.07
     solver
    0.06
    guards
    0.06
     herpes
    0.06
    ILD
    0.06
    .AspNetCore
    0.06
    اغ
    0.06
    나무
    0.06
     MyBase
    0.06
    宗
    0.06
    Act Density 0.293%

    No Known Activations