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

    Neuronpedia

    INDEX
    Explanations

    K or Q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MIT
    -0.07
    ルド
    -0.06
    Ê
    -0.06
    debit
    -0.06
    बल
    -0.06
     dungeon
    -0.06
    Christ
    -0.06
    Progress
    -0.06
     هنا
    -0.06
    esiz
    -0.06
    POSITIVE LOGITS
     applauded
    0.07
     actresses
    0.07
     plaintiffs
    0.07
     Noise
    0.07
     CIT
    0.07
    821
    0.06
    single
    0.06
    .Article
    0.06
     eighteen
    0.06
    >"↵
    0.06
    Act Density 0.004%

    No Known Activations