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

    Neuronpedia

    INDEX
    Explanations

    launching and planning actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    romo
    0.41
    শ্রে
    0.40
    lima
    0.39
    Frog
    0.38
     klas
    0.37
    Omn
    0.37
    Prod
    0.37
    Lime
    0.37
    AYS
    0.37
    Beam
    0.37
    POSITIVE LOGITS
     relaunch
    0.41
    に追加
    0.38
    ましたが
    0.38
    垷
    0.38
    )–
    0.37
    式
    0.37
    起動
    0.37
    upyter
    0.37
     Созда
    0.37
    应用程序
    0.36
    Act Density 0.000%

    No Known Activations