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

    Neuronpedia

    INDEX
    Explanations

    steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ism
    -0.06
    產品
    -0.06
    _package
    -0.06
     aumento
    -0.05
    ブラ
    -0.05
    ήλ
    -0.05
     程
    -0.05
     grades
    -0.05
     lineman
    -0.05
     ASAP
    -0.05
    POSITIVE LOGITS
     tại
    0.08
    .facebook
    0.07
    nton
    0.07
     Contributors
    0.07
    -fields
    0.07
    ــــــــ
    0.07
     Helmet
    0.06
     subscribe
    0.06
     lun
    0.06
    ≦
    0.06
    Act Density 0.003%

    No Known Activations