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

    Neuronpedia

    INDEX
    Explanations

    Prefaces and forewords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ویرایش
    -0.06
     learn
    -0.06
    sWith
    -0.06
     }],↵
    -0.06
     "))
    -0.06
    .actual
    -0.06
    руж
    -0.06
     hva
    -0.06
    ावन
    -0.06
     zásob
    -0.06
    POSITIVE LOGITS
     BAŞ
    0.08
    सत
    0.08
     Vladimir
    0.07
    ischer
    0.07
     mapStateToProps
    0.07
    ίνεται
    0.06
    ocking
    0.06
    ightly
    0.06
    ivement
    0.06
     resolutions
    0.06
    Act Density 0.012%

    No Known Activations