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

    Neuronpedia

    INDEX
    Explanations

    Teachers' resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mentor
    -0.08
     tug
    -0.07
     inward
    -0.07
     models
    -0.07
    뇌
    -0.07
    _uid
    -0.06
    /py
    -0.06
    民用
    -0.06
    .neg
    -0.06
     SVM
    -0.06
    POSITIVE LOGITS
    五一
    0.08
    pożycz
    0.08
     Hungarian
    0.08
    融化
    0.07
    )localObject
    0.07
    そ
    0.07
    犸
    0.07
    /File
    0.07
    湔
    0.07
     Oczywiście
    0.07
    Act Density 0.065%

    No Known Activations