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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    closest
    -0.07
     standalone
    -0.07
    _AspNet
    -0.07
     proving
    -0.07
    ☁
    -0.07
     hierarchy
    -0.07
     testament
    -0.07
     sacr
    -0.07
    คาร
    -0.06
    .setRequestHeader
    -0.06
    POSITIVE LOGITS
    教学
    0.08
     Plains
    0.08
    OUNDS
    0.07
     individ
    0.07
    ء
    0.07
     purchasers
    0.07
     appropri
    0.07
    이는
    0.07
    ائه
    0.07
    OWER
    0.07
    Act Density 0.001%

    No Known Activations